INDEX

Explanations

phrases related to changes or impacts on different entities or aspects

oai_token-act-pair · gpt-3.5-turbo

words associated with challenges or disruptions

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

earch

-0.64

OTAL

-0.62

 Receiver

-0.60

Subject

-0.60

 disobedience

-0.57

 Julius

-0.57

 Axis

-0.56

 Madison

-0.55

 Subject

-0.54

 loser

-0.54

POSITIVE LOGITS

been

1.30

kered

1.01

igrated

0.99

ked

0.94

oured

0.92

iated

0.89

urred

0.88

eded

0.88

gged

0.86

ayed

0.86

Activations Density 0.110%

phrases related to changes or impacts on different entities or aspects

words associated with challenges or disruptions

No Comments

No Known Activations