INDEX

Explanations

action verbs that involve some level of effort or achievement

oai_token-act-pair · gpt-3.5-turbo

actions associated with tasks, obligations, or responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

DragonMagazine

-0.72

ItemTracker

-0.61

soDeliveryDate

-0.56

blogspot

-0.56

itcher

-0.55

xtap

-0.54

likely

-0.54

pmwiki

-0.53

uploads

-0.53

Nos

-0.52

POSITIVE LOGITS

 oneself

0.89

uate

0.85

 them

0.77

enance

0.75

igate

0.73

urate

0.72

him

0.70

itate

0.70

 meaningful

0.66

ISE

0.65

Activations Density 0.623%

action verbs that involve some level of effort or achievement

actions associated with tasks, obligations, or responsibilities

No Comments

No Known Activations