INDEX

Explanations

words that end with 'r'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "r"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.70

cov

-0.69

eers

-0.68

eas

-0.64

creen

-0.62

 daylight

-0.58

 EntityItem

-0.58

 Tasman

-0.57

 paperback

-0.57

 propriet

-0.56

POSITIVE LOGITS

abbit

1.29

ussia

1.23

angers

1.16

acing

1.16

achel

1.14

agnar

1.14

ansom

1.13

outine

1.13

ific

1.10

ifle

1.09

Activations Density 0.045%

words that end with 'r'

occurrences of the letter "r"

No Comments

No Known Activations