INDEX

Explanations

mentions of the word "Gre" along with a number following it

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Gre" and its variations in context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

etheless

-0.78

ãģ§

-0.74

ãĥ¼ãĥ³

-0.73

ional

-0.72

ournal

-0.71

ãĥŁ

-0.71

ãĥ¼ãĥĨãĤ£

-0.68

orney

-0.65

unct

-0.65

-0.64

POSITIVE LOGITS

Gre

1.04

ogly

0.92

enery

0.89

gre

0.87

Gre

0.86

ase

0.82

yson

0.81

ety

0.80

edy

0.80

lev

0.79

Activations Density 0.003%

mentions of the word "Gre" along with a number following it

mentions of the name "Gre" and its variations in context

No Known Activations