INDEX

Explanations

references to 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 @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

-0.84

antage

-0.75

emetery

-0.72

odder

-0.71

vernment

-0.69

 Observatory

-0.68

PDATE

-0.66

 Skydragon

-0.65

undo

-0.65

atory

-0.65

POSITIVE LOGITS

 herself

1.50

pher

1.43

athed

1.27

athing

1.23

pard

1.21

pherd

1.11

ffield

1.10

ikh

0.99

ppard

0.98

lled

0.98

Activations Density 0.114%

references to the pronoun "she"

No Comments

No Known Activations