INDEX

Explanations

mentions of nonprofits and organizations

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 familiar

-0.67

 unsupported

-0.66

 embell

-0.64

 given

-0.63

 Geral

-0.63

fib

-0.63

 uncertain

-0.62

 linen

-0.61

 Bosnia

-0.61

 ILCS

-0.61

POSITIVE LOGITS

td

0.89

yne

0.89

uty

0.84

agonist

0.84

IDs

0.84

tarians

0.83

ifter

0.83

undle

0.82

eeper

0.82

eed

0.81

Activations Density 0.094%

mentions of nonprofits and organizations

acronyms or abbreviations

No Comments

No Known Activations