INDEX

Explanations

code comment syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AlterField

-0.60

()?;

-0.53

zyms

-0.52

astéro

-0.50

IRQn

-0.48

IsMutable

-0.47

 quæ

-0.47

%)$

-0.47

 informée

-0.47

ῦ

-0.46

POSITIVE LOGITS

 betweenstory

0.75

MemoryWarning

0.75

 OMITBAD

0.64

setVerticalGroup

0.64

 interp

0.58

 utafitiHapana

0.58

moveToFirst

0.57

:✨

0.55

 تكبرها

0.54



0.53

Activations Density 0.043%

code comment syntax

No Comments

No Known Activations