INDEX

Explanations

references to legal proceedings and related terminology

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

actions, decisions, plans, or responses

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

 otomatig

-0.51

CppMethod

-0.50

Зноскі

-0.49

 препратки

-0.49

 ddelweddau

-0.49

الدراسه

-0.47

prnewswire

-0.47

GTCX

-0.47

 sumpay

-0.46

 وتسجيلات

-0.46

POSITIVE LOGITS

ⓧ

0.50

↹

0.47

évaluateur

0.47

Din

0.42

 tastes

0.39

Din

0.39

yyj

0.38

ílio

0.38

 Citizen

0.36

Activations Density 0.075%

references to legal proceedings and related terminology

actions, decisions, plans, or responses

No Comments

No Known Activations