INDEX

Explanations

mentions of specific names or topics

oai_token-act-pair · gpt-3.5-turbo

the word "mentioned" and its variations in various contexts

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

uilt

-0.75

eware

-0.70

usterity

-0.70

earned

-0.69

otypes

-0.69

orneys

-0.69

iership

-0.68

inals

-0.67

heres

-0.67

onew

-0.66

POSITIVE LOGITS

 mentioning

1.03

 mentions

0.97

 mentioned

0.84

lihood

0.80

 aloud

0.80

 mention

0.76

 Prelude

0.71

 above

0.71

REDACTED

0.68

 prominently

0.68

Activations Density 0.010%

mentions of specific names or topics

the word "mentioned" and its variations in various contexts

No Comments

No Known Activations