INDEX

Explanations

references to toys and their safety standards

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

toy descriptions

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

rungsseite

-0.51

+#+#

-0.51

 zijne

-0.48

riceps

-0.48

 Paglinawan

-0.47

\{\\

-0.46

loem

-0.44

GIVEREF

-0.44

 ExecuteAsync

-0.43

 Constitution

-0.43

POSITIVE LOGITS

 toys

0.93

toy

0.75

 Toys

0.73

toys

0.65

Toys

0.60

玩具

0.60

 kids

0.60

 mainan

0.59

toy

0.58

 juguetes

0.57

Activations Density 0.017%

references to toys and their safety standards

toy descriptions

No Comments

No Known Activations