INDEX

Explanations

numeric values or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

apol

-0.60

 lievito

-0.60

 σύν

-0.53

ástico

-0.52

 lenker

-0.52

 zucca

-0.50

tagHelperRunner

-0.50

 Aufenthal

-0.49

督

-0.48

 camicia

-0.48

POSITIVE LOGITS

TagMode

0.65

0.64

interopRequire

0.64

LabelTagHelper

0.62

WriteLiteral

0.61

hdashline

0.58

*/;

0.56

*/,

0.56

LLocation

0.56

onViewCreated

0.55

Activations Density 0.404%

numeric values or counts

No Comments

No Known Activations