INDEX

Explanations

phrases mentioning various organizations and their statements or actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of punctuation marks, specifically commas

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

worldly

-0.76

 transgress

-0.65

 generations

-0.62

lust

-0.62

Availability

-0.59

 intensity

-0.58

actual

-0.57

 eligibility

-0.57

fall

-0.57

 gust

-0.55

POSITIVE LOGITS

0.84

otos

0.78

 wrote

0.75

 congratulated

0.74

 commented

0.71

 agrees

0.70

 urged

0.70

told

0.70

 advises

0.68

achu

0.67

Activations Density 0.179%

phrases mentioning various organizations and their statements or actions

occurrences of punctuation marks, specifically commas

No Comments

No Known Activations