INDEX

Explanations

references to structure, organization, and categories within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

WebVitals

-0.69

 varandra

-0.63

migrationBuilder

-0.63

 naturlig

-0.62

ఔ

-0.61

 Réponses

-0.61

 frequenza

-0.60

 ErrIntOverflow

-0.59

SwingConstants

-0.57

IZABETH

-0.56

POSITIVE LOGITS

 initComponents

0.58

DoubleQuotes

0.57

aarrggbb

0.56

 unit

0.54

 group

0.53

 work

0.52

 EconPapers

0.49

 program

0.48

 choices

0.47

 offered

0.47

Activations Density 1.347%

references to structure, organization, and categories within a context

No Comments

No Known Activations