INDEX

Explanations

references to a proven track record or history, particularly in a professional or achievement context

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

history of

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

things

-0.36

clusão

-0.35

 skär

-0.34

 sarili

-0.32

 téléph

-0.31

FU

-0.31

soccer

-0.31

house

-0.31

 mágico

-0.31

CONFIGURATION

-0.31

POSITIVE LOGITS

 pinulongan

0.69

 BorderSide

0.65

 successful

0.64

 historial

0.63

 reputation

0.63

verifyException

0.62

proven

0.60

 proven

0.58

 reputations

0.58

 history

0.57

Activations Density 0.018%

references to a proven track record or history, particularly in a professional or achievement context

history of

No Comments

No Known Activations