INDEX

Explanations

references to law enforcement and stress-related contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.88

endphp

-0.81

UnusedPrivate

-0.75

-0.71

ArgsConstructor

-0.69

المشاركات

-0.69

новниш

-0.68

 GetEnumerator

-0.68

HtmlAttribute

-0.67

UIControlState

-0.65

POSITIVE LOGITS

 Einf

0.49

دانشنامهٔ

0.45

 DbSet

0.45

淋

0.43

این

0.43

 Poste

0.43

 Evange

0.43

 Lehre

0.43

 LoginForm

0.43

 Trocken

0.42

Activations Density 0.140%

references to law enforcement and stress-related contexts

No Comments

No Known Activations