INDEX

Explanations

elements related to Python class definitions and their representations

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

AsStream

-0.63

DoubleQuotes

-0.61

providedIn

-0.56

Hochspringen

-0.56

/**

-0.54

orianCalendar

-0.53

/*

-0.51

GraphicsUnit

-0.51

 utafitiHapana

-0.50

addCriterion

-0.50

POSITIVE LOGITS

repr

0.90

 Repr

0.60

 repr

0.60

 rép

0.57

Rep

0.48

 Reps

0.47

Rep

0.47

 plegable

0.46

rep

0.44

rep

0.44

Activations Density 0.002%

elements related to Python class definitions and their representations

No Comments

No Known Activations