INDEX

Explanations

words related to consistency and conformity

oai_token-act-pair · gpt-3.5-turbo

terms related to consistency and reliable adherence to standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

doors

-0.85

olit

-0.77

OTOS

-0.75

rection

-0.74

worms

-0.72

pez

-0.71

crow

-0.71

stals

-0.71

kamp

-0.70

pathy

-0.69

POSITIVE LOGITS

itarian

0.90

 consistency

0.83

ially

0.81

 offender

0.80

ively

0.80

iated

0.80

ently

0.79

ibly

0.78

ITY

0.77

GoldMagikarp

0.76

Activations Density 0.028%

words related to consistency and conformity

terms related to consistency and reliable adherence to standards

No Comments

No Known Activations