INDEX

Explanations

expressions of political aggression and accusations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

idental

-0.45

 effet

-0.39

IntoConstraints

-0.38

 generally

-0.38

 initial

-0.38

 free

-0.38

 priori

-0.34

«

-0.34

Ur

-0.33

 relatively

-0.33

POSITIVE LOGITS

Jereo

0.89

 cowardice

0.86

StructEnd

0.84

 للمعارف

0.83

 مرئيه

0.81

 AssemblyCulture

0.80

PreferredItem

0.79

RegressionTest

0.79

MethodManager

0.76

DockStyle

0.76

Activations Density 0.594%

expressions of political aggression and accusations

No Comments

No Known Activations