INDEX

Explanations

terms related to specific actions or events in a professional or organizational context, such as freezing hiring, staffing, finances, or bonuses

oai_token-act-pair · gpt-3.5-turbo

topics related to societal issues and personal circumstances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alike

-0.60

 Sect

-0.58

ggles

-0.57

nant

-0.55

asms

-0.53

humans

-0.52

iverse

-0.47

phant

-0.47

gger

-0.47

 greatness

-0.47

POSITIVE LOGITS

and

0.79

or

0.73

0.60

pection

0.57

staking

0.56

creen

0.55

 respons

0.54

 identifying

0.53

 "$:/

0.52

Activations Density 1.280%

terms related to specific actions or events in a professional or organizational context, such as freezing hiring, staffing, finances, or bonuses

topics related to societal issues and personal circumstances

No Comments

No Known Activations