INDEX

Explanations

mentions of widespread occurrences or beliefs

oai_token-act-pair · gpt-3.5-turbo

references to widespread phenomena or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

estamp

-0.80

ħĭ

-0.75

cair

-0.74

thur

-0.71

tein

-0.71

aminer

-0.71

rament

-0.70

izons

-0.69

wives

-0.67

Khe

-0.65

POSITIVE LOGITS

 worldwide

0.88

 widespread

0.88

ãĥ¥

0.86

 dissemination

0.85

 misconception

0.81

 adoption

0.80

wealth

0.80

 nationwide

0.78

spread

0.76

ãĥĩãĤ£

0.76

Activations Density 0.017%

mentions of widespread occurrences or beliefs

references to widespread phenomena or issues

No Comments

No Known Activations