INDEX

Explanations

programming-related terminology and structures

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

extAlignment

-0.77

webElementXpaths

-0.75

 noDo

-0.72

 <>",

-0.71

awtextra

-0.69

parsedMessage

-0.67

AndEndTag

-0.67

 NSCoder

-0.66

invokeLater

-0.66

 CURIAM

-0.65

POSITIVE LOGITS

 schema

0.47

 schemas

0.41

 fiche

0.40

 cadastro

0.38

 layout

0.38

schema

0.38

cadastro

0.36

 Schema

0.36

 Registration

0.36

 cadast

0.36

Activations Density 0.042%

programming-related terminology and structures

No Comments

No Known Activations