INDEX

Explanations

documents or text passages where something is written or authored by someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "written" in various contexts

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

nel

-0.89

Ĭ±

-0.83

nels

-0.82

ugal

-0.81

 Shinra

-0.76

abe

-0.75

isters

-0.73

aho

-0.71

xon

-0.70

illon

-0.70

POSITIVE LOGITS

 instrument

0.72

 typed

0.71

acters

0.70

 excerpts

0.70

 written

0.70

escription

0.69

itatively

0.68

 detailing

0.67

 advising

0.67

 consent

0.66

Activations Density 0.029%

documents or text passages where something is written or authored by someone

instances of the word "written" in various contexts

No Comments

No Known Activations