INDEX

Explanations

contextual references to political bias and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rrggbb

-0.71

Демографія

-0.68

 }}"></

-0.64

 emer

-0.62

 intermit

-0.56

redirected

-0.56

cemment

-0.55

enderror

-0.54

 AssemblyProduct

-0.52

hibli

-0.51

POSITIVE LOGITS

 outcome

0.72

注定

0.71

 doomed

0.71

 predetermined

0.68

 inevitable

0.65

outcome

0.62

ReusableCell

0.59

 already

0.57

 precon

0.56

 Вікіпе

0.55

Activations Density 0.294%

contextual references to political bias and investigations

No Comments

No Known Activations