INDEX

Explanations

technical terms and vocabulary related to software and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Chham

-0.57

)<\

-0.56

AnimationsModule

-0.56

 BoxFit

-0.56

Kjelder

-0.54

ModelBuilder

-0.52

']],

-0.50

'},

-0.48

sidemargin

-0.48

 roligt

-0.48

POSITIVE LOGITS

 AssemblyCulture

0.66

المناصب

0.61

RegressionTest

0.59

Билгалдахарш

0.58

EDEFAULT

0.56

 selfish

0.55

multirow

0.55

 continúas

0.55

 autob

0.54

acağına

0.54

Activations Density 1.837%

technical terms and vocabulary related to software and programming

No Comments

No Known Activations