INDEX

Explanations

phrases indicating the utilization of items or entities for specific purposes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "used."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Hai

-0.78

bitious

-0.70

 Roose

-0.65

nesty

-0.61

 Niet

-0.60

alos

-0.60

Pis

-0.60

 undertaking

-0.58

Rid

-0.57

 Gord

-0.57

POSITIVE LOGITS

 sparing

1.11

fully

0.92

 interchange

0.91

 captcha

0.80

pez

0.79

 extensively

0.78

 exclusively

0.77

FUL

0.74

 wisely

0.73

ragon

0.72

Activations Density 0.075%

phrases indicating the utilization of items or entities for specific purposes

occurrences of the word "used."

No Comments

No Known Activations