INDEX

Explanations

proper nouns, specifically names and titles

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

proper names

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

ftagPool

-0.93

aarrggbb

-0.93

IntoConstraints

-0.91

 queſta

-0.89

AsUp

-0.81

⟬

-0.80

 חיצוניים

-0.76

tinyos

-0.76

Попис

-0.75

adaptiveStyles

-0.75

POSITIVE LOGITS

0.86

0.62

0.61

0.60

0.57

0.56

0.54

↵

0.54

Activations Density 0.059%

proper nouns, specifically names and titles

proper names

No Comments

No Known Activations