INDEX

Explanations

mentions of tar sands and related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of tar sands and related environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

fecture

-0.72

tymology

-0.72

redit

-0.68

 redundancy

-0.67

yright

-0.64

ntil

-0.64

ernandez

-0.63

rities

-0.63

uilt

-0.63

 Prob

-0.62

POSITIVE LOGITS

 sands

1.35

 Sands

1.03

ĸļ

0.83

boro

0.81

gow

0.79

wagon

0.77

cape

0.76

heet

0.76

 Wast

0.73

 wastes

0.73

Activations Density 0.010%

mentions of tar sands and related terms

mentions of tar sands and related environments

No Comments

No Known Activations