INDEX

Explanations

specific measurements and descriptions of properties or neighborhoods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 estekak

-0.69

BIÉN

-0.56

erdo

-0.53

 виправивши

-0.52

 billig

-0.52

 Fenne

-0.52

pixmap

-0.52

TUM

-0.52

 kaynağından

-0.51

HttpFoundation

-0.51

POSITIVE LOGITS

 entertain

0.68

 entertaining

0.67

ArrowToggle

0.62

 master

0.61

 bedrooms

0.60

 living

0.60

 entertainers

0.59

 entertainer

0.58

 spacious

0.57

 home

0.56

Activations Density 0.034%

specific measurements and descriptions of properties or neighborhoods

No Comments

No Known Activations