INDEX

Explanations

structured data representations, likely related to programming or configuration files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 RIPRODUZIONE

-0.56

if

-0.55

ThemeOverlay

-0.52

cstdio

-0.49

Touches

-0.49

 sujetos

-0.48

usleep

-0.47

 preuve

-0.47

 saja

-0.47

 pyplot

-0.47

POSITIVE LOGITS

 kasarigan

0.96

 onAnimation

0.76

principalColumn

0.71

ContentAsync

0.67

MigrationBuilder

0.64

 وتسجيلات

0.63

 Réponses

0.63

QMetaType

0.63

},{

0.59

 సౌకర్య

0.59

Activations Density 0.103%

structured data representations, likely related to programming or configuration files

No Comments

No Known Activations