INDEX

Explanations

statements expressing agreement

oai_token-act-pair · gpt-3.5-turbo

expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 typh

-0.79

gins

-0.71

oufl

-0.71

 Gutenberg

-0.65

 Roads

-0.65

agin

-0.65

anus

-0.65

ogo

-0.63

thur

-0.61

æµ

-0.61

POSITIVE LOGITS

 vehemently

0.89

ably

0.81

 disagree

0.80

lihood

0.79

 unanimously

0.76

rences

0.76

SOURCE

0.75

abl

0.69

atively

0.68

ault

0.68

Activations Density 0.046%

statements expressing agreement

expressions of agreement

No Comments

No Known Activations