INDEX

Explanations

mentions of headings or categories within longer texts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating completeness or additional information in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Ïī

-0.89

ifice

-0.72

adr

-0.71

assic

-0.68

livion

-0.68

pron

-0.66

––

-0.65

 âĢ¦"

-0.63

orney

-0.62

ugh

-0.62

POSITIVE LOGITS

 Examples

1.21

 Locations

1.16

 Results

1.15

 Features

1.14

 Thoughts

1.12

 Contents

1.07

 Names

1.04

 Stories

1.02

 Problems

1.02

 Analysis

1.01

Activations Density 0.215%

mentions of headings or categories within longer texts

phrases indicating completeness or additional information in a narrative

No Comments

No Known Activations