INDEX

Explanations

legal and regulatory compliance language

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

prevented items, similar usage, target prosecutions

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

Toast

-0.43

TV

-0.41

 Toast

-0.40

 rame

-0.40

 good

-0.40

 Bear

-0.40

 gypsy

-0.39

 toast

-0.39

Tel

-0.39

 great

-0.39

POSITIVE LOGITS

RenderAtEndOf

0.66

+#+#

0.58

BagConstraints

0.49

 budou

0.49

 künftig

0.48

fromnode

0.47

 prohibits

0.47

osexuality

0.47

новниш

0.46

principalColumn

0.45

Activations Density 0.039%

legal and regulatory compliance language

prevented items, similar usage, target prosecutions

No Comments

No Known Activations