INDEX

Explanations

references to World War II

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

OGR

-0.80

obook

-0.71

ITY

-0.70

*/(

-0.67

Asset

-0.65

 snipp

-0.65

 metab

-0.62

KE

-0.61

 answ

-0.61

 mathemat

-0.61

POSITIVE LOGITS

II

0.99

lord

0.95

lords

0.94

III

0.92

bler

0.82

planes

0.79

ombat

0.79

riors

0.79

rior

0.77

XVI

0.74

Activations Density 0.009%

references to World War II

No Comments

No Known Activations