INDEX

Explanations

specialized formatting or symbols used in mathematical expressions or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

مراجع

-0.67

<bos>

-0.57

 Règlement

-0.56

codecs

-0.55

 preocu

-0.54

 Selecciona

-0.54

 typique

-0.53

 potrivit

-0.53

RegressionTest

-0.53

 Мексичка

-0.53

POSITIVE LOGITS

}{

0.80

/}{

0.79

Slf

0.67

ValueStyle

0.66

 jspb

0.64

 doInBackground

0.61

unknownFields

0.61

AccessorTable

0.58

 Normdatei

0.58

istoitu

0.57

Activations Density 0.145%

specialized formatting or symbols used in mathematical expressions or structures

No Comments

No Known Activations