INDEX

Explanations

references to governmental and political actions or events related to elections and interference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.45

bre

-0.44

 kỳ

-0.42

-0.41

BitmapFactory

-0.40

牌

-0.40

rõ

-0.40

kiet

-0.40

smöglichkeiten

-0.39

POSITIVE LOGITS

 kasarigan

1.27

IntoConstraints

1.15

aarrggbb

0.91

хьтан

0.91

########.

0.90

 مرئيه

0.90

Datuak

0.89

Autoritní

0.87

 فريبيس

0.86

Efq

0.86

Activations Density 0.360%

references to governmental and political actions or events related to elections and interference

No Comments

No Known Activations