INDEX

Explanations

references to academic names and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 <=",

-0.73



-0.63

KURZBESCHREIBUNG

-0.62

irited

-0.61

psack

-0.61

Personendaten

-0.60

########.

-0.59

ⓧ

-0.57

msgTypes

-0.57

IContainer

-0.57

POSITIVE LOGITS

 Rusia

0.60

 Russia

0.55

发表于

0.55

 Russland

0.53

 paździer

0.52

 روسیه

0.51

їна

0.51

asteroide

0.50

 Russie

0.49

latego

0.48

Activations Density 0.133%

references to academic names and affiliations

No Comments

No Known Activations