INDEX

Explanations

words related to interaction and connection between different entities or elements

oai_token-act-pair · gpt-3.5-turbo

references to interconnectedness and relationships

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

aughs

-0.72

\\\\\\\\

-0.71

DragonMagazine

-0.71

ongs

-0.69

FUL

-0.68

ggle

-0.65

OCK

-0.63

ggies

-0.63

å£«

-0.63

hyde

-0.63

POSITIVE LOGITS

lude

1.05

racial

1.04

continental

1.01

dimensional

0.95

locking

0.95

disciplinary

0.92

stitial

0.91

cession

0.89

connect

0.89

mitt

0.88

Activations Density 0.014%

words related to interaction and connection between different entities or elements

references to interconnectedness and relationships

No Comments

No Known Activations