INDEX

Explanations

Roman numerals and page numbers in a document

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation marks in the text

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

itiz

-0.81

umers

-0.80

onga

-0.78

enza

-0.76

isine

-0.75

 glim

-0.74

oling

-0.73

entially

-0.68

itaire

-0.68

atonin

-0.68

POSITIVE LOGITS

 Retrieved

0.82

 Aires

0.75

 Geological

0.74

Eng

0.73

+)

0.71

III

0.69

icio

0.68

REDACTED

0.65

 Cornel

0.65

wikipedia

0.65

Activations Density 0.093%

Roman numerals and page numbers in a document

instances of punctuation marks in the text

No Comments

No Known Activations