INDEX

Explanations

specific geographic locations and associated names in the text

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

antiation

-0.60

genstein

-0.59

 StringTokenizer

-0.57

dorff

-0.57

__(/*!

-0.57

Бахар

-0.56

ACTERS

-0.56

dingen

-0.55

ESSOR

-0.55

lably

-0.55

POSITIVE LOGITS

цездатний

0.55

Controllo

0.53

WithIOException

0.51

 lolita

0.48

 Logs

0.44

 areia

0.42

 useAppContext

0.42

=#{

0.42

 verstor

0.42

 Türkei

0.42

Activations Density 0.101%

specific geographic locations and associated names in the text

No Comments

No Known Activations