INDEX

Explanations

written text

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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Ĭ±

-0.79

nel

-0.78

ĪĴ

-0.76

abol

-0.75

nels

-0.73

agara

-0.72

EGA

-0.67

 Shinra

-0.65

Sensor

-0.63

tnc

-0.63

POSITIVE LOGITS

 aloud

0.93

acters

0.81

by

0.79

itatively

0.78

escription

0.76

 collabor

0.76

 expressly

0.75

 excerpts

0.73

 contempor

0.72

 pseudonym

0.71

Activations Density 0.036%

written text

instances of the word "written" in various contexts

No Comments

No Known Activations