INDEX

Explanations

references to news shows and appearances related to political commentary

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

news shows and talk shows

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 DriverManager

-0.40

 انتشار

-0.38

oa̍t

-0.38

 JpaRepository

-0.38

 Mert

-0.36

aarrggbb

-0.36

 Hütte

-0.36

antrag

-0.36

 envi

-0.35

方案

-0.35

POSITIVE LOGITS

 CNBC

0.54

 spokes

0.54

 utafitiHapana

0.53

Personensuche

0.47

 snippetHide

0.47

WaitGroup

0.46

Personendaten

0.46

 seyn

0.46

ніципалі

0.45

tagext

0.45

Activations Density 0.038%

references to news shows and appearances related to political commentary

news shows and talk shows

No Comments

No Known Activations