INDEX

Explanations

code-related terms and Java-specific syntax

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

AccessorTable

-0.79

WireFormatLite

-0.70

CodedInputStream

-0.66

mergeFrom

-0.65

SerializedSize

-0.65

EndContext

-0.65

发表于

-0.64

Portail

-0.64

 Waray

-0.62

MergeFrom

-0.62

POSITIVE LOGITS

 javafx

0.94

FXML

0.75

scene

0.72

FX

0.66

fxml

0.66

Scene

0.65

 scene

0.64

FX

0.63

fx

0.60

 "..\..\

0.58

Activations Density 0.040%

code-related terms and Java-specific syntax

No Comments

No Known Activations