INDEX

Explanations

names of public figures or people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Reloaded

-0.82

ccording

-0.77

 eleph

-0.72

assetsadobe

-0.66

CLASSIFIED

-0.66

 exting

-0.65

lihood

-0.65

 ACTION

-0.65

 laun

-0.65

 tremend

-0.64

POSITIVE LOGITS

aney

0.88

enson

0.88

kel

0.81

chuk

0.81

ikarp

0.80

ucci

0.80

oval

0.79

ison

0.77

mond

0.77

jan

0.76

Activations Density 0.181%

names of public figures or people

proper nouns, particularly names of individuals

No Comments

No Known Activations