INDEX

Explanations

words related to ownership or possession

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "our"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

conom

-0.84

icter

-0.79

puff

-0.79

endra

-0.75

fect

-0.71

hift

-0.70

cum

-0.69

bender

-0.69

ppings

-0.68

wrap

-0.68

POSITIVE LOGITS

selves

1.24

own

1.05

 beloved

0.98

 ourselves

0.95

 dear

0.88

 asses

0.87

 ancestors

0.86

 esteemed

0.85

 hearts

0.85

 selves

0.84

Activations Density 0.144%

words related to ownership or possession

occurrences of the word "our"

No Comments

No Known Activations