INDEX

Explanations

references to text formatting, especially focusing on the word "format"

oai_token-act-pair · gpt-3.5-turbo

mentions of different text formats and formatting instructions

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

roma

-0.85

doms

-0.80

arma

-0.75

hiro

-0.72

worth

-0.70

guard

-0.70

nee

-0.68

ĺħ

-0.67

 Michele

-0.66

vironment

-0.66

POSITIVE LOGITS

ters

1.04

ting

0.83

atted

0.82

 format

0.79

tered

0.77

tering

0.74

 formats

0.74

etter

0.72

aldehyde

0.71

furt

0.70

Activations Density 0.037%

references to text formatting, especially focusing on the word "format"

mentions of different text formats and formatting instructions

No Comments

No Known Activations