INDEX

Explanations

mentions of specific features in a software or product

oai_token-act-pair · gpt-3.5-turbo

references to features in technology or software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hiba

-0.77

externalActionCode

-0.76

azar

-0.73

apy

-0.72

cale

-0.70

 decl

-0.67

 kindergarten

-0.65

sis

-0.65

ears

-0.63

sei

-0.63

POSITIVE LOGITS

Feature

1.01

ttes

0.93

lich

0.92

feature

0.90

 features

0.87

Features

0.85

 Features

0.83

features

0.82

 feature

0.78

ivity

0.75

Activations Density 0.017%

mentions of specific features in a software or product

references to features in technology or software

No Comments

No Known Activations