INDEX

Explanations

proper nouns consisting of the letters "Sha"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and prominent individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anwhile

-0.88

ktop

-0.87

etheless

-0.82

gran

-0.81

olesc

-0.75

ications

-0.72

ollower

-0.71

icted

-0.71

ancy

-0.70

ĨĴ

-0.70

POSITIVE LOGITS

IELD

0.86

roud

0.78

ning

0.73

rike

0.71

pler

0.71

ned

0.70

IFT

0.69

ful

0.69

ivas

0.68

pling

0.68

Activations Density 0.058%

proper nouns consisting of the letters "Sha"

mentions of specific names and prominent individuals

No Comments

No Known Activations