INDEX

Explanations

terms related to points, awards, and reputation within a system or context

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

bonus points

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ArrowToggle

-0.54

 initComponents

-0.53

 BoxFit

-0.52

tagHelperRunner

-0.52

 ब्रेकडाउन

-0.51

原始内容存档于

-0.49

CppMethod

-0.48

 препратки

-0.47

المراجع

-0.47

istoitu

-0.46

POSITIVE LOGITS

 points

0.47

 brownie

0.45

 bonus

0.44

Points

0.42

 reward

0.42

 POINTS

0.40

 rewards

0.40

Hauptartikel

0.37

 Points

0.35

 coins

0.35

Activations Density 0.165%

terms related to points, awards, and reputation within a system or context

bonus points

No Comments

No Known Activations