INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

paksa

-0.62

Хьажоргаш

-0.61

ⓧ

-0.58

евич

-0.57

xito

-0.57

verket

-0.56

 témoins

-0.56

 eingestellt

-0.55

⁩

-0.55

 Allgemeinen

-0.55

POSITIVE LOGITS

 Sack

0.66

Mad

0.63

 kaarangay

0.62

Mad

0.55

ofire

0.54

 تضيفلها

0.54

AccessLevel

0.51

 numerator

0.51

 Sher

0.51

Neg

0.50

Activations Density 0.215%

proper nouns, particularly names of individuals

No Comments

No Known Activations