INDEX

Explanations

proper nouns in a mixed list

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and organizations

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

arily

-0.79

iple

-0.73

apers

-0.73

 Nadu

-0.69

imo

-0.69

iership

-0.68

asons

-0.66

ively

-0.66

isable

-0.65

ASON

-0.65

POSITIVE LOGITS

wana

0.97

halla

0.83

keley

0.80

achev

0.79

EGIN

0.79

axter

0.78

hari

0.78

ruary

0.75

cham

0.75

bent

0.74

Activations Density 0.142%

proper nouns in a mixed list

proper nouns, particularly names and organizations

No Comments

No Known Activations