INDEX

Explanations

instances of the word "more" in various contexts, indicating a focus on comparisons or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Majefty

-0.64

expandindo

-0.64

 ſmall

-0.62

 Reſ

-0.61

IContainer

-0.61

 وتسجيلات

-0.61

lapsingToolbar

-0.59

DockStyle

-0.58

webElementXpaths

-0.58

ulously

-0.56

POSITIVE LOGITS

 like

0.67

 suited

0.57

 akin

0.56

 likely

0.55

more

0.54

 interested

0.53

getColumnIndex

0.51

}))

0.50

Revenir

0.49

 скорее

0.49

Activations Density 0.118%

instances of the word "more" in various contexts, indicating a focus on comparisons or quantities

No Comments

No Known Activations