INDEX

Explanations

programming-related keywords and structure indicators within code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

thâu

-0.92

MigrationBuilder

-0.87

Хьажоргаш

-0.86

enumi

-0.78

Datuak

-0.78

URLException

-0.76

ServerSocket

-0.76

 виправивши

-0.75

 XCTest

-0.74

 Makefile

-0.73

POSITIVE LOGITS

Begin

1.25

BEGIN

1.21

 Begin

1.17

 BEGIN

1.14

 begin

1.03

 start

0.85

 Start

0.84

End

0.82

Start

0.79

 begins

0.79

Activations Density 0.026%

programming-related keywords and structure indicators within code

No Comments

No Known Activations