INDEX

Explanations

proper nouns and titles

oai_token-act-pair · gpt-3.5-turbo

punctuation and specific structures related to releases and titles of creative works

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

hod

-0.70

hap

-0.70

xon

-0.70

nas

-0.69

bley

-0.67

icons

-0.67

onomy

-0.66

"@

-0.65

isch

-0.65

 arsen

-0.65

POSITIVE LOGITS

feat

0.92

 Remastered

0.86

 anthology

0.84

 starring

0.83

ebted

0.74

 Volume

0.74

 sequels

0.71

 Redux

0.71

 sequel

0.70

 finale

0.70

Activations Density 0.412%

proper nouns and titles

punctuation and specific structures related to releases and titles of creative works

No Comments

No Known Activations