INDEX

Explanations

names of cast members and characters in films

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

names and places

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

بوابة

-0.56

ReusableCell

-0.54

 tartalomajánló

-0.53

IsContent

-0.47

Som

-0.47

actively

-0.46

locally

-0.45

-------------</

-0.45

Tazama

-0.44

 Réponses

-0.44

POSITIVE LOGITS

 respectively

0.44

 gynhyrchwyd

0.41

protoimpl

0.39

eraard

0.38

 respectivamente

0.38

 antigüedad

0.36

 together

0.36

 Paglinawan

0.34

respectively

0.34

 disagreed

0.33

Activations Density 0.028%

names of cast members and characters in films

names and places

No Comments

No Known Activations