INDEX

Explanations

references to structured data elements, likely in programming or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

\{\\

-0.64

httphttps

-0.62

Архівовано

-0.56

 ModelExpression

-0.55

ftance

-0.54

efit

-0.53

pierw

-0.52

chale

-0.52

"):

-0.52

 Matth

-0.52

POSITIVE LOGITS

WebElementEntity

0.66

Rüyada

0.64

 TextAppearance

0.61

aarrggbb

0.61

 ligiloj

0.60

 rêves

0.58

ⓧ

0.57

лтамалар

0.56

 Baillargeon

0.56

円

0.56

Activations Density 0.925%

references to structured data elements, likely in programming or mathematical contexts

No Comments

No Known Activations