INDEX

Explanations

mentions of statistical data related to the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States or its abbreviations and variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inances

-0.64

tions

-0.63

operator

-0.63

errors

-0.61

NK

-0.61

members

-0.60

merce

-0.60

ticket

-0.60

sbm

-0.59

bot

-0.59

POSITIVE LOGITS

 Midwest

0.79

 Dollar

0.75

 waterways

0.72

 Indies

0.72

 Territories

0.70

 Hudson

0.69

 Isles

0.69

outheastern

0.67

 Northeast

0.67

 spotlight

0.67

Activations Density 0.117%

mentions of statistical data related to the United States

references to the United States or its abbreviations and variations

No Comments

No Known Activations