INDEX

Explanations

coding-related function calls and error checks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

rü

-0.49

GroupLayout

-0.47

 <<<<<<<<<<<<<<

-0.43

 MessageBoxIcon

-0.42

FileDialog

-0.42

φε

-0.41

 oprot

-0.40

beitet

-0.40

statusCode

-0.39

 гра

-0.39

POSITIVE LOGITS

ImageContext

1.02

脚注の使い方

0.96

NameInMap

0.75

 nahilalakip

0.72

UrlResolution

0.70

CrossRef

0.67

原始内容存档于

0.66

 noDo

0.66

存于互联网档案馆

0.65

ècie

0.64

Activations Density 0.153%

coding-related function calls and error checks

No Comments

No Known Activations