INDEX

Explanations

numerical values and citations, often referencing legal contexts or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Worst

-0.46

 visibilité

-0.44

プション

-0.43

 tega

-0.43

 fidélité

-0.42

 fuerzas

-0.41

Ingredi

-0.41

 bring

-0.41

γκ

-0.40

 pitié

-0.39

POSITIVE LOGITS

complexContent

1.06

RTDA

0.81

Brainz

0.75

脚注の使い方

0.70

MigrationBuilder

0.68

ьаж

0.67

 تعدى

0.67

BufferException

0.66

 gyhoeddwyd

0.66

StoryboardSegue

0.66

Activations Density 0.429%

numerical values and citations, often referencing legal contexts or documentation

No Comments

No Known Activations