INDEX

Explanations

references to the quality or seriousness of various situations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

etsk

-0.78

uba

-0.76

pload

-0.74

monton

-0.73

olulu

-0.72

illion

-0.71

icia

-0.70

tackle

-0.69

puff

-0.69

aft

-0.68

POSITIVE LOGITS

 entire

1.05

 respective

1.00

 aforementioned

0.95

 latter

0.93

 preceding

0.92

 individual

0.91

 smallest

0.89

 universe

0.83

 current

0.81

 relationship

0.81

Activations Density 0.315%

references to the quality or seriousness of various situations

occurrences of the word "the."

No Comments

No Known Activations