INDEX

Explanations

phrases related to a female individual named "She."

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun indicating a female subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INGTON

-0.68

 Skydragon

-0.68

atory

-0.62

kefeller

-0.61

ornia

-0.60

assing

-0.60

busters

-0.59

 Starg

-0.58

~~~~

-0.57

 Disclosure

-0.57

POSITIVE LOGITS

pherd

1.45

pher

1.30

pard

1.26

ffield

1.16

ppard

1.16

athed

1.09

athing

1.07

ldon

1.03

'll

1.01

itage

0.99

Activations Density 0.098%

phrases related to a female individual named "She."

instances of the pronoun indicating a female subject

No Comments

No Known Activations