INDEX

Explanations

elements related to structured command definitions and logging functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.66

='%

-0.52

 Witkin

-0.47

tifkan

-0.47

PerformLayout

-0.46

出版年

-0.44

LikeLike

-0.44

енча

-0.43

ticons

-0.43

>);

-0.43

POSITIVE LOGITS

 nahilalakip

0.81

 كومونز

0.63

ArrowToggle

0.61

[{

0.61

'{

0.60

 autorytatywna

0.58

"{

0.57

 Roskov

0.57

__*/

0.56

 Administrativna

0.55

Activations Density 0.104%

elements related to structured command definitions and logging functions

No Comments

No Known Activations