INDEX

Explanations

words related to a specific topic or entity, specifically "Yakupov"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of specific entities, particularly names and terms associated with conflict or violence

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

enegger

-0.88

erer

-0.69

atcher

-0.67

-0.66

lections

-0.65

egg

-0.64

å£«

-0.64

smanship

-0.63

ascript

-0.63

erning

-0.63

POSITIVE LOGITS

usha

0.89

veyard

0.88

ashtra

0.87

acly

0.87

izons

0.85

andon

0.80

nect

0.80

agall

0.78

oga

0.77

akh

0.76

Activations Density 0.038%

words related to a specific topic or entity, specifically "Yakupov"

repeated mentions of specific entities, particularly names and terms associated with conflict or violence

No Comments

No Known Activations