INDEX

Explanations

references to numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.17.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

脚注の使い方

-0.80

 nahilalakip

-0.69

migrationBuilder

-0.67

__*/

-0.67

)];

-0.63

锈钢

-0.62

tonode

-0.62

*/].

-0.60

Distribuzione

-0.57

amitié

-0.55

POSITIVE LOGITS

RunWith

0.67

 life

0.57

lif

0.54

ExtendWith

0.54

 Assignee

0.52

 extinct

0.50

 Life

0.50

 lifes

0.50

ConstraintMaker

0.50

">—

0.49

Activations Density 0.139%

references to numerical data or statistics

No Comments

No Known Activations