INDEX

Explanations

references to others or external parties in relation to actions or mistakes

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

DOS

-0.78

endon

-0.70

Increases

-0.69

osterone

-0.68

UES

-0.68

leys

-0.67

 Highlights

-0.66

ooming

-0.65

 Centers

-0.65

undown

-0.65

POSITIVE LOGITS

worldly

1.25

 entirely

0.81

quin

0.78

 besides

0.76

 than

0.73

 else

0.73

 unrelated

0.70

udic

0.69

swer

0.66

 forgot

0.65

Activations Density 0.021%

references to others or external parties in relation to actions or mistakes

No Comments

No Known Activations