INDEX

Explanations

mentions of policy decisions and legal actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "can" indicating potential actions or capabilities

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

chel

-0.65

 Mant

-0.62

irection

-0.60

furt

-0.59

Maker

-0.58

 paradigm

-0.57

 Federation

-0.57

boss

-0.57

Sense

-0.57

 Sandwich

-0.56

POSITIVE LOGITS

't

1.43

adian

1.09

 attest

1.08

isters

1.06

NOT

1.01

berra

0.98

 afford

0.97

 easily

0.93

ISTER

0.91

 decide

0.90

Activations Density 0.151%

mentions of policy decisions and legal actions

instances of the word "can" indicating potential actions or capabilities

No Comments

No Known Activations