INDEX

Explanations

mentions of workshops

oai_token-act-pair · gpt-3.5-turbo

references to workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

croft

-0.68

bis

-0.64

 overw

-0.62

 rewritten

-0.61

terior

-0.61

pend

-0.60

sey

-0.60

 basal

-0.59

entity

-0.59

emic

-0.57

POSITIVE LOGITS

smanship

0.97

yrinth

0.93

 Workshop

0.80

 workshop

0.78

craft

0.75

rador

0.73

 srfAttach

0.73

dayName

0.73

Works

0.72

kit

0.71

Activations Density 0.013%

mentions of workshops

references to workshops

No Comments

No Known Activations