INDEX

Explanations

descriptions of things as "nice"

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "nice."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

arians

-0.79

ogens

-0.79

authorized

-0.79

arers

-0.76

arian

-0.75

ochond

-0.75

inant

-0.74

rained

-0.74

uilding

-0.71

igate

-0.69

POSITIVE LOGITS

 nice

0.92

bye

0.86

 fluffy

0.81

bye

0.80

 touches

0.78

 additions

0.78

 little

0.75

 enough

0.75

 neat

0.74

 bonus

0.74

Activations Density 0.019%

descriptions of things as "nice"

the repeated use of the word "nice."

No Comments

No Known Activations