INDEX

Explanations

phrases indicating a high level of confidence or suspicion

oai_token-act-pair · gpt-3.5-turbo

expressions of certainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

artney

-0.79

irlf

-0.76

cial

-0.73

idelines

-0.70

packs

-0.68

ife

-0.66

uit

-0.66

fund

-0.65

 bonding

-0.65

isting

-0.64

POSITIVE LOGITS

poke

0.76

ļé

0.75

£ı

0.70

é¾į

0.69

Ļ½

0.69

 Rasmussen

0.63

âĶĢâĶĢâĶĢâĶĢ

0.63

Īè

0.62

 myself

0.62

 admission

0.62

Activations Density 0.132%

phrases indicating a high level of confidence or suspicion

expressions of certainty or doubt

No Comments

No Known Activations