INDEX

Explanations

sequences of symbols and formatting typically found in programming or markup code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

NameInMap

-0.65

 defaultstate

-0.64

errHandler

-0.62

 CURIAM

-0.59

 InputDecoration

-0.58

IContainer

-0.58

cdnjs

-0.56

 صوتيه

-0.56

bootstrapcdn

-0.55

ptonshire

-0.55

POSITIVE LOGITS

 disponibilités

0.61

 Abonnez

0.48

-*-

0.48

toma

0.47

زه

0.45

uffy

0.44

^{*}=

0.42

 power

0.42

ArgsConstructor

0.41

Puissance

0.41

Activations Density 0.106%

sequences of symbols and formatting typically found in programming or markup code

No Comments

No Known Activations