INDEX

Explanations

references and terminology related to APIs and their definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.38

delwed

-0.36

im

-0.36

-0.35

 super

-0.35

 spent

-0.34

-0.33

 Mejía

-0.33

Watch

-0.33

POSITIVE LOGITS

ApiModelProperty

0.78

AutoScaleMode

0.70

 surla

0.70

ConstraintMaker

0.69

 AssemblyVersion

0.68

 ModelExpression

0.67

httphttps

0.67

 JpaRepository

0.66

 ProtoMessage

0.65

 AspNetCore

0.65

Activations Density 0.012%

references and terminology related to APIs and their definitions

No Comments

No Known Activations