INDEX

Explanations

entities or concepts indicated by '|' characters

oai_token-act-pair · gpt-3.5-turbo

the letter 'G', possibly indicating a focus on brands, organizations, or significant terms that begin with "G"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 compr

-0.77

ĸļ

-0.70

 estab

-0.69

ĺħ

-0.68

htt

-0.66

oÄŁ

-0.63

terday

-0.63

 provision

-0.61

 craw

-0.61

 crowded

-0.58

POSITIVE LOGITS

roups

1.07

uild

1.02

RAY

0.97

iants

0.96

reens

0.96

ONE

0.95

ossip

0.94

AMES

0.94

raphic

0.92

Ps

0.91

Activations Density 0.024%

entities or concepts indicated by '|' characters

the letter 'G', possibly indicating a focus on brands, organizations, or significant terms that begin with "G"

No Comments

No Known Activations