INDEX

Explanations

phrases or expressions indicating a request for assistance or hints

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

makeatother

-0.52

例文帳に追加

-0.52

న్ని

-0.50

mentaux

-0.50

 Grüsse

-0.50

 lemari

-0.50

Gambas

-0.49

rinol

-0.49

AFX

-0.49

 plotly

-0.48

POSITIVE LOGITS

RenderAtEndOf

0.97

 Roskov

0.78

parsedMessage

0.72

UnknownFieldSet

0.60

ItemBackground

0.58

webElementXpaths

0.57

 propOrder

0.57

 EconPapers

0.57

stdc

0.56

contentLoaded

0.56

Activations Density 0.003%

phrases or expressions indicating a request for assistance or hints

No Comments

No Known Activations