INDEX

Explanations

punctuation marks and formatting in programming or markup contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

出版年

-0.71

parsedMessage

-0.64

 snippetHide

-0.60

 NSCoder

-0.54

 StringVar

-0.51

 EconPapers

-0.50

UpInside

-0.50

principalTable

-0.45

RectangleBorder

-0.45

rror

-0.45

POSITIVE LOGITS

yntaxException

0.42

 fieldNum

0.40

EndGlobalSection

0.39

zugehen

0.38

ientôt

0.37

作用

0.35

RegressionTest

0.35

ValueStyle

0.33

rungsseite

0.33

トッピング

0.33

Activations Density 0.051%

punctuation marks and formatting in programming or markup contexts

No Comments

No Known Activations