INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

key figures and names associated with philosophical arguments or critiques

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

»Ĵ

-0.71

 Apex

-0.67

ĸļ

-0.65

 fetch

-0.65

å§«

-0.64

ngth

-0.64

 relocate

-0.64

acion

-0.63

 lookout

-0.62

 pinch

-0.62

POSITIVE LOGITS

 philosophers

0.87

omsky

0.87

 Krugman

0.82

 Feminist

0.81

 Chomsky

0.78

galitarian

0.77

 argues

0.76

 theorists

0.74

otle

0.74

 proponents

0.73

Activations Density 0.569%

proper nouns or names

key figures and names associated with philosophical arguments or critiques

No Comments

No Known Activations