INDEX

Explanations

references to geographical locations or specific attributes related to locations

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

 ModelExpression

-0.55

最快更新

-0.48

tona

-0.44

MessageTagHelper

-0.44

 esternos

-0.44

 adhered

-0.43

tonode

-0.43

ManagedBean

-0.42

ⓧ

-0.41

tonsoft

-0.41

POSITIVE LOGITS

featureID

0.55

 snippetHide

0.45

 TextAppearance

0.42

/\.

0.40

 précie

0.38

ViewFeatures

0.38

 quả

0.37

GTCX

0.37

migrationBuilder

0.36

\{\\

0.36

Activations Density 0.075%

references to geographical locations or specific attributes related to locations

No Comments

No Known Activations