INDEX

Explanations

sections of text categorized under specific labels or headings

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

orsi

-0.76

imer

-0.72

chers

-0.71

ighters

-0.71

uras

-0.69

anza

-0.68

isma

-0.64

ilant

-0.63

asar

-0.63

mine

-0.62

POSITIVE LOGITS

Unc

0.87

 Tags

0.85

 Categories

0.83

 Articles

0.76

 Occupations

0.75

 POLIT

0.74

 Miscellaneous

0.72

 Comments

0.72

 Conspiracy

0.71

 Discrimination

0.71

Activations Density 0.012%

sections of text categorized under specific labels or headings

No Comments

No Known Activations