INDEX

Explanations

expressions indicating a significant quantity or intensity

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

"much" or "much more"

np_acts-logits-general · gemini-2.0-flash

much to extent or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.76

Composable

-0.61

cinogenicity

-0.57

featureID

-0.57

SequentialGroup

-0.55

athyroid

-0.54

Vidite

-0.54

TypedDataSet

-0.53

astéro

-0.51

TokenNameLPAREN

-0.48

POSITIVE LOGITS

 much

0.82

 many

0.81

Much

0.71

 Much

0.69

 MUCH

0.68

 muchos

0.67

 Many

0.67

 MANY

0.67

 Beaucoup

0.65

much

0.64

Activations Density 0.327%

expressions indicating a significant quantity or intensity

"much" or "much more"

much to extent or comparison

No Comments

No Known Activations