INDEX

Explanations

mentions of the word "West", sometimes preceded by a direction.

oai_token-act-pair · gemini-2.0-flash

references to "West"

np_token-act-pair-logits · gpt-4o-mini

West

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.76

AsUp

-0.59

 GetEnumerator

-0.57

featureID

-0.57

Chham

-0.56

didSet

-0.56

 captivity

-0.55

 مرئيه

-0.54

CopyWith

-0.54

Reentrant

-0.53

POSITIVE LOGITS

TX

0.52

queryInterface

0.51

+#+#

0.48

 للاسماء

0.48

Становништво

0.47

RenderAtEndOf

0.46

ph

0.45

φ

0.45

TX

0.44

 Poehler

0.43

Activations Density 0.160%

mentions of the word "West", sometimes preceded by a direction.

references to "West"

West

No Comments

No Known Activations