INDEX

Explanations

information related to locations and distances

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate significant events or milestones

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

 Aval

-0.72

orate

-0.66

sterdam

-0.62

orer

-0.60

 lifes

-0.58

 estranged

-0.57

ades

-0.57

 bullied

-0.56

 agon

-0.56

 ecstatic

-0.56

POSITIVE LOGITS

pmwiki

0.92

Reason

0.92

Article

0.89

GROUND

0.87

................................................................

0.86

âĸł

0.83

Myth

0.83

----------------------------------------------------------------

0.79

Chicken

0.78

Rank

0.78

Activations Density 0.229%

information related to locations and distances

phrases that indicate significant events or milestones

No Comments

No Known Activations