INDEX

Explanations

references to customized or custom-made products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ï¸

-0.83

trump

-0.78

loo

-0.75

 CrossRef

-0.71

Æ

-0.70

gdala

-0.70

minster

-0.70

wick

-0.69

 Lauder

-0.68

·

-0.68

POSITIVE LOGITS

isable

1.69

izations

1.58

izable

1.43

ised

1.40

isations

1.39

isation

1.27

arily

1.27

ization

1.12

ized

1.08

izing

1.08

Activations Density 0.019%

references to customized or custom-made products or services

No Comments

No Known Activations