INDEX

Explanations

words related to occupations or roles within a community

oai_token-act-pair · gpt-3.5-turbo

words with the suffix "-er," indicating roles, professions, or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SIZE

-0.78

emetery

-0.75

ãĥĥãĥī

-0.75

ī

-0.74

Lead

-0.67

ori

-0.67

chwitz

-0.65

ĳ

-0.65

ĳå£«

-0.64

ĸļå£«

-0.64

POSITIVE LOGITS

 extraord

1.55

 beware

0.93

gery

0.90

stakes

0.84

izer

0.73

jack

0.72

digy

0.70

glers

0.69

oad

0.67

agonist

0.66

Activations Density 0.218%

words related to occupations or roles within a community

words with the suffix "-er," indicating roles, professions, or characteristics

No Comments

No Known Activations