INDEX

Explanations

prepositions indicating locations or relationships

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

SourceChecksum

-0.52

OGND

-0.39

TypedDataSet

-0.37



-0.35

MENAFN

-0.35

NameInMap

-0.34

Ingredienti

-0.33

™.

-0.31

ji

-0.31

RefNanny

-0.31

POSITIVE LOGITS

migrationBuilder

0.63

RenderAtEndOf

0.58

 विश्वसनीयता

0.57

帖最后由

0.56

ftagPool

0.52

 auffi

0.50

 ſind

0.49

costa

0.47

Viitteet

0.47

AutoScaleMode

0.47

Activations Density 0.074%

prepositions indicating locations or relationships

No Comments

No Known Activations