INDEX

Explanations

information or explanations about specific topics or concepts

oai_token-act-pair · gpt-3.5-turbo

empty or non-informative text segments

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

psc

-0.61

Prime

-0.58

omever

-0.57

ividually

-0.56

sole

-0.56

 helicop

-0.56

sic

-0.55

enegger

-0.54

ovan

-0.54

Pg

-0.53

POSITIVE LOGITS

 nutshell

0.69

 fascinating

0.65

 âĢº

0.62

 topics

0.62

 myths

0.61

 misconceptions

0.61

 perspectives

0.60

 overview

0.59

 Difference

0.58

 basics

0.58

Activations Density 0.506%

information or explanations about specific topics or concepts

empty or non-informative text segments

No Comments

No Known Activations