INDEX

Explanations

instances of the word "wrong"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "wrong" and its variations in various contexts

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

zeb

-0.68

hens

-0.66

Fn

-0.64

lished

-0.64

hedral

-0.63

arov

-0.63

lov

-0.63

incinn

-0.62

electric

-0.62

 Flavoring

-0.62

POSITIVE LOGITS

fully

0.91

headed

0.82

sight

0.79

ftime

0.77

 unfocusedRange

0.74

eous

0.74

 premise

0.73

 guiActiveUn

0.72

dest

0.72

ed

0.71

Activations Density 0.022%

instances of the word "wrong"

instances of the word "wrong" and its variations in various contexts

No Comments

No Known Activations