INDEX

Explanations

terms related to political positions and elections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ธ์

-0.52

StartTag

-0.48

ւ

-0.47

iedades

-0.47

Until

-0.46

Slf

-0.46

ยม

-0.46

 BoxFit

-0.45

ására

-0.45

揄

-0.44

POSITIVE LOGITS

NgModule

0.63

erialized

0.59

::<

0.54

 Bioaccumulative

0.53

viewDidLoad

0.53

fortawesome

0.52

Gens

0.52

ItemBackground

0.51

 estimés

0.51

RenderAtEndOf

0.51

Activations Density 0.645%

terms related to political positions and elections

No Comments

No Known Activations