INDEX

Explanations

phrases related to involvement or action

oai_token-act-pair · gpt-3.5-turbo

references to systems and structures in operation or influence

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

zzy

-0.80

quickShipAvailable

-0.71

aren

-0.67

 corrid

-0.66

oute

-0.62

milo

-0.62

ynt

-0.62

zes

-0.61

redit

-0.60

USH

-0.60

POSITIVE LOGITS

 guise

0.85

ability

0.63

lia

0.63

ividual

0.62

 vicinity

0.61

lessness

0.58

 form

0.57

 hierarchy

0.56

 relativity

0.56

 fashion

0.55

Activations Density 0.172%

phrases related to involvement or action

references to systems and structures in operation or influence

No Comments

No Known Activations