INDEX

Explanations

specific scientific or technical terminology, especially in research and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

enumii

-0.75

 للاسماء

-0.67

 nakalista

-0.59

 ModelExpression

-0.59

findpost

-0.58

 Corbu

-0.58

 Exactos

-0.54

 protoimpl

-0.52

帖

-0.52

 flyknit

-0.52

POSITIVE LOGITS

Bite

0.70

mouth

0.68

 textStatus

0.67

 bite

0.67

bite

0.64

 belly

0.62

Xna

0.62

 tooth

0.61

PRNewswire

0.60

Mouth

0.59

Activations Density 2.550%

specific scientific or technical terminology, especially in research and programming contexts

No Comments

No Known Activations