INDEX

Explanations

references to specific events, timelines, or occurrences related to data and data handling processes

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

before or after

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

存于互联网档案馆

-0.48

ailles

-0.35

iskt

-0.34

reserve

-0.33

뀔

-0.32

Ban

-0.32

sĩ

-0.32

建

-0.31

 linha

-0.31

 vejo

-0.31

POSITIVE LOGITS

 ویکی‌پدی

0.66

 ProtoMessage

0.62

ThroughAttribute

0.61

MessageTagHelper

0.56

providedIn

0.56

parsedMessage

0.54

localctx

0.54

PreferredItem

0.52

nextProps

0.52

UnusedPrivate

0.50

Activations Density 0.049%

references to specific events, timelines, or occurrences related to data and data handling processes

before or after

No Comments

No Known Activations