INDEX

Explanations

technical terms related to layers and layering in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TargetException

-0.63

 OnInit

-0.59

ActionPerformed

-0.57

 GenerationType

-0.56

Naissance

-0.54

 MainAxisSize

-0.53

openhauer

-0.52

jsonwebtoken

-0.50

SwingConstants

-0.47

NewUrlParser

-0.46

POSITIVE LOGITS

 layer

0.95

 Layer

0.94

 layers

0.94

 LAYER

0.90

 Layers

0.87

Layer

0.84

layer

0.83

layers

0.81

 layering

0.74

 Schicht

0.73

Activations Density 0.316%

technical terms related to layers and layering in various contexts

No Comments

No Known Activations