INDEX

Explanations

programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

rrggbb

-0.80

AsUp

-0.77

ंदीखरीदारी

-0.75

ьаж

-0.73

 kasarigan

-0.71

UnsafeEnabled

-0.70

WireFormatLite

-0.70

 MenuView

-0.68

 '\\;'

-0.67

LabelTagHelper

-0.67

POSITIVE LOGITS

enumi

0.68

tagHelperRunner

0.57

 насељу

0.48

⟹

0.44

="../../

0.42

BeginContext

0.40

 gekle

0.40

BoxShadow

0.40

tableFuture

0.40

imba

0.39

Activations Density 0.393%

programming-related terms and concepts

No Comments

No Known Activations