INDEX

Explanations

references to torture

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Darkness

-0.76

lihood

-0.74

FORE

-0.69

 donor

-0.66

Â·Â·

-0.66

 Dangerous

-0.65

 livest

-0.65

IST

-0.65

 Farn

-0.64

âĸ¬

-0.63

POSITIVE LOGITS

oise

1.52

urous

1.50

uring

1.15

ured

1.11

illas

1.09

urers

1.08

imer

1.08

uous

1.07

eur

1.03

ures

1.03

Activations Density 0.003%

references to torture

No Comments

No Known Activations