INDEX

Explanations

phrases indicating degrees of comparison and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 senare

-0.57

 hueco

-0.57

bekistan

-0.56

日起

-0.55

 Tagged

-0.55

 normalement

-0.54

 supplémentaire

-0.53

 normalidad

-0.53

 tidligere

-0.53

حياته

-0.53

POSITIVE LOGITS

 تضيفلها

0.95

 viewDidLoad

0.73

AddHtmlAttribute

0.72

RectangleBorder

0.65

far

0.65

Демографія

0.64

StrictEqual

0.61

findpost

0.61

Nationalité

0.61

Sucesor

0.60

Activations Density 0.150%

phrases indicating degrees of comparison and evaluation

No Comments

No Known Activations