INDEX

Explanations

keywords related to power and authority

oai_token-act-pair · gpt-3.5-turbo

the letter 's.'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

EStream

-0.79

 Leilan

-0.67

EStreamFrame

-0.66

uliffe

-0.66

 fuss

-0.63

 duplicate

-0.61

SIGN

-0.61

FINE

-0.60

 Presidents

-0.58

electric

-0.58

POSITIVE LOGITS

ources

1.18

omew

1.05

ourced

1.04

ouls

1.04

atisf

1.02

ourcing

1.01

lightly

0.96

wered

0.96

iblings

0.96

kaya

0.95

Activations Density 0.422%

keywords related to power and authority

the letter 's.'

No Comments

No Known Activations