INDEX

Explanations

references to the pronoun "she" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the pronoun "she."

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

kefeller

-0.73

church

-0.68

atory

-0.67

 Disclosure

-0.65

 Unlimited

-0.64

~~~~

-0.64

 Flavoring

-0.63

fit

-0.63

 Glob

-0.61

 Jimmy

-0.61

POSITIVE LOGITS

pher

1.46

athed

1.24

pherd

1.23

pard

1.20

ffield

1.13

'd

1.11

athing

1.09

'll

1.06

ppard

1.00

ldon

0.93

Activations Density 0.109%

references to the pronoun "she" in various contexts

occurrences of the pronoun "she."

No Comments

No Known Activations