INDEX

Explanations

phrases related to personal interactions with a female individual

oai_token-act-pair · gpt-3.5-turbo

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

ypes

-1.04

ype

-0.98

kefeller

-0.92

ornia

-0.87

arios

-0.82

VERTIS

-0.76

ollo

-0.74

ormons

-0.72

ozy

-0.70

eers

-0.70

POSITIVE LOGITS

ding

1.29

 husband

1.23

own

1.20

metic

1.17

cule

1.16

 daughter

1.16

nia

1.07

 granddaughter

1.05

 Majesty

1.04

ded

1.04

Activations Density 0.113%

phrases related to personal interactions with a female individual

No Comments

No Known Activations