INDEX

Explanations

phrases related to errors or mistakes

oai_token-act-pair · gpt-3.5-turbo

phrases related to errors and mistakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

utic

-0.78

esses

-0.76

natureconservancy

-0.75

itant

-0.74

gins

-0.74

enture

-0.73

igree

-0.72

kees

-0.72

 showc

-0.71

nis

-0.69

POSITIVE LOGITS

 omission

0.96

 Reincarn

0.71

 Niet

0.71

 Andersen

0.70

 Baird

0.68

 Citation

0.67

 Loki

0.66

 Kelley

0.65

fusc

0.65

Gow

0.64

Activations Density 0.544%

phrases related to errors or mistakes

phrases related to errors and mistakes

No Comments

No Known Activations