INDEX

Explanations

mentions of therapeutic treatments

oai_token-act-pair · gpt-3.5-turbo

the term "ape" in various contexts

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

sf

-0.77

sch

-0.76

 Beir

-0.75

naires

-0.75

-0.73

naire

-0.72

 Niet

-0.71

 Kling

-0.69

quickShipAvailable

-0.68

 Lowry

-0.68

POSITIVE LOGITS

utic

1.18

utics

1.03

etus

0.97

apers

0.86

olitan

0.86

aukee

0.84

iatrics

0.83

insula

0.78

urity

0.76

ilon

0.75

Activations Density 0.035%

mentions of therapeutic treatments

the term "ape" in various contexts

No Comments

No Known Activations