INDEX

Explanations

phrases related to challenging or reviewing actions by authority figures

oai_token-act-pair · gpt-3.5-turbo

instances of the word "by" indicating actions or authorship

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

 resil

-0.79

ãĤ¦ãĤ¹

-0.78

 "$:/

-0.75

redits

-0.70

stakes

-0.68

tenance

-0.67

adal

-0.66

meat

-0.65

URN

-0.64

qqa

-0.64

POSITIVE LOGITS

 virtue

1.03

laws

0.96

products

0.95

gone

0.85

product

0.78

 omission

0.77

 proxy

0.72

 policymakers

0.69

 whistleblowers

0.69

 politicians

0.69

Activations Density 0.122%

phrases related to challenging or reviewing actions by authority figures

instances of the word "by" indicating actions or authorship

No Comments

No Known Activations