INDEX

Explanations

assertions related to political actions or statements and their implications

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

history, historical, historically

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.85

 transfieras

-0.63

 otomatig

-0.60

期刊论文

-0.58

DataAnnotations

-0.57

MLLoader

-0.57

IBOutlet

-0.55

cipais

-0.53

جغرافيا

-0.53

Климат

-0.52

POSITIVE LOGITS

 history

1.88

history

1.61

 historically

1.55

 historical

1.51

History

1.49

 past

1.45

 History

1.43

 histories

1.37

 HISTORY

1.36

 histórico

1.35

Activations Density 0.104%

assertions related to political actions or statements and their implications

history, historical, historically

No Comments

No Known Activations