INDEX

Explanations

instances of the word "this" with various context

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ĭ±

-0.88

ARS

-0.76

ographies

-0.73

pots

-0.71

Ĵ

-0.70

aughed

-0.70

»Ĵ

-0.70

oller

-0.69

KNOWN

-0.69

Ħ

-0.68

POSITIVE LOGITS

 latest

0.99

 represents

0.96

 week

0.95

isn

0.94

is

0.91

 election

0.89

 constitutes

0.88

 proves

0.87

 endeavor

0.87

 particular

0.87

Activations Density 0.172%

instances of the word "this" with various context

No Comments

No Known Activations