INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 horizont

-0.89

 horr

-0.88

 Thumbnails

-0.79

 hemor

-0.79

 behav

-0.77

iP

-0.77

ASC

-0.74

 livest

-0.73

 multic

-0.73

 multip

-0.72

POSITIVE LOGITS

enei

1.22

owsky

1.22

ovich

1.13

iani

1.11

owitz

1.07

awi

1.06

ati

1.03

cki

1.01

gger

0.99

olini

0.99

Activations Density 0.238%

proper nouns

proper nouns, particularly names and titles

No Comments

No Known Activations