INDEX

Explanations

references to showers or bathing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

migrationBuilder

-0.68

msgTypes

-0.59

 MonoBehaviour

-0.59

TypedDataSet

-0.58

 meille

-0.56

 Italijani

-0.56

RegistryLite

-0.55

 Einladung

-0.54

发表于

-0.53

TabIndex

-0.52

POSITIVE LOGITS

 Crown

0.70

LookAnd

0.61

 crown

0.61

Crown

0.59

exp

0.58

 Kingdom

0.57

 kingdom

0.56

 shower

0.53

crown

0.50

 Shower

0.48

Activations Density 0.193%

references to showers or bathing contexts

No Comments

No Known Activations