INDEX

Explanations

mathematical symbols and notations related to statistical expressions or equations

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

Tokens before the volume number in citations

np_acts-logits-general · gemini-2.0-flash

parenthesized/bracketed numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 AssemblyCulture

-0.75

GEBURTSDATUM

-0.72

rungsseite

-0.64

Portale

-0.64

Bism

-0.56

 препратки

-0.56

 defaultstate

-0.54

setVerticalGroup

-0.53

ItemBackground

-0.53

 bezeichneter

-0.53

POSITIVE LOGITS

Suppl

0.65

 Spec

0.62

Spec

0.61

special

0.61

 special

0.60

 specials

0.59

supp

0.59

ESPEC

0.59

Supplement

0.58

Special

0.57

Activations Density 0.106%

mathematical symbols and notations related to statistical expressions or equations

Tokens before the volume number in citations

parenthesized/bracketed numbers

No Comments

No Known Activations