INDEX

Explanations

mentions of puppets

oai_token-act-pair · gpt-3.5-turbo

references to puppets and puppet-related concepts

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

ythm

-0.70

-0.69

 DATA

-0.67

 Mobility

-0.66

ambling

-0.65

ENDED

-0.65

IRO

-0.65

FORMATION

-0.64

IFT

-0.64

================================================================

-0.64

POSITIVE LOGITS

regate

0.97

emort

0.95

uppet

0.90

eer

0.85

emark

0.84

enhagen

0.83

flix

0.82

merce

0.80

ovie

0.79

yip

0.78

Activations Density 0.041%

mentions of puppets

references to puppets and puppet-related concepts

No Comments

No Known Activations