INDEX

Explanations

references to data analysis and classification processes

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

ChildScrollView

-0.81

 vapa

-0.65

AutoresizingMask

-0.64

CloseOperation

-0.63

extAlignment

-0.62

AxisAlignment

-0.61

 fraî

-0.59

 snippetHide

-0.58

SourceChecksum

-0.58

 abenço

-0.57

POSITIVE LOGITS

 basketball

0.90

 baseball

0.85

 football

0.81

 soccer

0.80

 Basketball

0.74

 volleyball

0.73

 tennis

0.71

 dentistry

0.69

 aviation

0.69

 tobacco

0.69

Activations Density 1.867%

references to data analysis and classification processes

No Comments

No Known Activations