INDEX

Explanations

names of individuals and significant historical figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

%)$

-0.77

ÉM

-0.75

siez

-0.71

ViewImports

-0.70

omation

-0.68

oine

-0.68

bode

-0.68

eaway

-0.67

."</

-0.65

INTEN

-0.65

POSITIVE LOGITS

 himself

0.91

0.79

’

0.68

 Himself

0.62

himself

0.61

ssohn

0.59

 Seeder

0.55

who

0.54

 nødven

0.54

 desnuda

0.54

Activations Density 0.339%

names of individuals and significant historical figures

No Comments

No Known Activations