INDEX

Explanations

phrases related to traveling and transportation

oai_token-act-pair · gpt-3.5-turbo

references to luggage and artwork

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

mega

-0.73

arb

-0.70

bern

-0.69

eln

-0.69

neys

-0.66

erate

-0.65

ital

-0.64

otin

-0.63

sole

-0.63

ulner

-0.62

POSITIVE LOGITS

shed

0.86

tesy

0.77

flows

0.68

works

0.68

channelAvailability

0.66

 surrounds

0.66

 surfaces

0.64

pmwiki

0.64

pieces

0.63

 spilled

0.63

Activations Density 0.068%

phrases related to traveling and transportation

references to luggage and artwork

No Comments

No Known Activations