INDEX

Explanations

numeric values and symbols related to data or measurements

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

figures/tables

np_acts-logits-general · gemini-2.0-flash

technical reference identifiers

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

RenderAtEndOf

-0.61

Referanser

-0.51

 мәкал

-0.50

GTCX

-0.49

 Chwiliwch

-0.49

twimg

-0.48

 Administrativna

-0.47

 vettoriale

-0.46

Réalisation

-0.42

 cầu

-0.40

POSITIVE LOGITS

HomeAsUp

0.43

Parcelize

0.42

RectangleBorder

0.41

LTRB

0.39

genossen

0.38

VID

0.37

FontOfSize

0.36

msgSender

0.36

ItemID

0.36

 '\\;'

0.36

Activations Density 2.658%

numeric values and symbols related to data or measurements

figures/tables

technical reference identifiers

No Comments

No Known Activations