INDEX

Explanations

words related to specific objects or items such as "Ring", "stamp", "bell", and "helmet"

oai_token-act-pair · gpt-3.5-turbo

nouns related to objects and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inez

-0.68

actionDate

-0.67

cca

-0.64

NetMessage

-0.63

arily

-0.62

ional

-0.60

 advers

-0.59

iddy

-0.57

nesota

-0.56

 Finance

-0.56

POSITIVE LOGITS

washer

0.93

 pictured

0.88

maker

0.82

 holder

0.75

 cutter

0.73

wright

0.72

 maker

0.71

 Replacement

0.68

worm

0.67

 Holder

0.66

Activations Density 0.542%

words related to specific objects or items such as "Ring", "stamp", "bell", and "helmet"

nouns related to objects and items

No Comments

No Known Activations