INDEX

Explanations

references to specific individuals involved in political contexts, particularly related to the Trump campaign

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

ĸļ

-0.91

 Curiosity

-0.79

ĪĴ

-0.78

 à¨

-0.73

Redd

-0.72

@#&

-0.71

ĨĴ

-0.71

ï¸

-0.68

RAL

-0.68

ä¸ī

-0.68

POSITIVE LOGITS

afort

1.30

 Manafort

0.87

uchin

0.84

agements

0.80

 indicted

0.79

iola

0.75

agement

0.75

 resigned

0.74

hattan

0.71

ufact

0.70

Activations Density 0.003%

references to specific individuals involved in political contexts, particularly related to the Trump campaign

No Comments

No Known Activations