INDEX

Explanations

the word "Casper"

oai_token-act-pair · gpt-3.5-turbo

occurrences of certain names or proper nouns

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITNESS

-0.85

ĸļ

-0.79

ovych

-0.74

ailability

-0.70

 reckoning

-0.70

dfx

-0.66

Â¯

-0.65

prises

-0.64

 occup

-0.62

etheless

-0.62

POSITIVE LOGITS

rano

0.83

olini

0.81

cius

0.80

chio

0.80

zzi

0.79

neau

0.79

jas

0.74

illin

0.72

iani

0.71

opa

0.70

Activations Density 0.224%

the word "Casper"

occurrences of certain names or proper nouns

No Comments

No Known Activations