INDEX

Explanations

starts of new sections or paragraphs in a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Next" indicating a sequence or continuation in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lees

-0.66

kay

-0.64

zinski

-0.62

ocker

-0.61

ans

-0.61

arbon

-0.61

acons

-0.59

ondon

-0.58

ogether

-0.57

ITH

-0.57

POSITIVE LOGITS

 Steps

1.10

door

1.04

 week

0.98

 steps

0.96

 month

0.94

 Generation

0.92

 generation

0.87

 Month

0.86

 door

0.85

 year

0.85

Activations Density 0.028%

starts of new sections or paragraphs in a text

instances of the word "Next" indicating a sequence or continuation in a text

No Comments

No Known Activations