INDEX

Explanations

phrases related to giving instructions or setting guidelines

oai_token-act-pair · gpt-3.5-turbo

the presence of specific characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 vulner

-0.79

 mathemat

-0.73

 suspic

-0.68

 disadvant

-0.67

 pyramid

-0.67

 Mirage

-0.67

 Pyramid

-0.66

 disliked

-0.66

 elig

-0.64

 seiz

-0.64

POSITIVE LOGITS

ï¸ı

1.01

own

0.85

ution

0.83

auts

0.82

tale

0.82

iversary

0.81

ence

0.81

save

0.81

east

0.80

Activations Density 0.046%

phrases related to giving instructions or setting guidelines

the presence of specific characters or symbols

No Comments

No Known Activations