INDEX

Explanations

mentions of specific names or locations, particularly with the letters 'vern' included

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "vern" and related names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

raid

-0.73

FTA

-0.63

give

-0.62

 horizontal

-0.62

upon

-0.61

Torrent

-0.61

©¶æ

-0.60

OHN

-0.60

Wan

-0.60

ELF

-0.59

POSITIVE LOGITS

acular

1.34

sburg

1.03

ues

0.95

lishing

0.88

issance

0.87

unci

0.87

insula

0.86

ormal

0.83

ocity

0.82

Activations Density 0.013%

mentions of specific names or locations, particularly with the letters 'vern' included

occurrences of the word "vern" and related names

No Comments

No Known Activations