INDEX

Explanations

specific names and proper nouns associated with individuals and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

OGND

-0.68

verwijspagina

-0.54

XtraGrid

-0.54

 ThemeData

-0.53

withIdentifier

-0.52



-0.51

 ujednoznacz

-0.50

EndGlobalSection

-0.48

BeginContext

-0.47

galo

-0.47

POSITIVE LOGITS

ides

0.67

 proviso

0.63

IDES

0.62

essen

0.59

sson

0.59

onson

0.58

AILABLE

0.57

 loginUser

0.56

 umana

0.55

insen

0.54

Activations Density 0.215%

specific names and proper nouns associated with individuals and brands

No Comments

No Known Activations