INDEX

Explanations

mentions of corruption and ethical violations in political contexts

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

Tokens preceding claims/accusations

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 ModelExpression

-0.60

 שוליים

-0.58

⟬

-0.57

ſelf

-0.55

 initComponents

-0.54

出版年

-0.52

 Jefus

-0.51

Рис

-0.51

 enfans

-0.51

 ourselves

-0.50

POSITIVE LOGITS

 تكبرها

0.40

0.38

Hentet

0.37

 banged

0.37

.«

0.36

 criticised

0.35

 lesz

0.35

 ***!

0.35

Напомним

0.35

 disillusion

0.35

Activations Density 0.079%

mentions of corruption and ethical violations in political contexts

Tokens preceding claims/accusations

No Comments

No Known Activations