INDEX

Explanations

code-related comments and documentation

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

AndEndTag

-0.66

NameInMap

-0.51

DllImport

-0.46

migrationBuilder

-0.46

tagHelper

-0.45

TextSpan

-0.43

__*/

-0.43

tri

-0.43

irs

-0.42

[++

-0.42

POSITIVE LOGITS

')")

0.74

 Réponses

0.63

 فريبيس

0.63

EndInit

0.61

livejournal

0.60

Personensuche

0.60

 ſome

0.60

 ſaid

0.58

 preſent

0.58

 zitate

0.58

Activations Density 0.138%

code-related comments and documentation

No Comments

No Known Activations