INDEX

Explanations

punctuation marks and formatting characters used in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

featureID

-1.19

abestanden

-0.94

 يتيمه

-0.89

]--;

-0.88

PerformLayout

-0.83

WriteBarrier

-0.82

 Administrativna

-0.80

RenderAtEndOf

-0.80

 Roskov

-0.78

 odkazy

-0.77

POSITIVE LOGITS

 present

0.56

‘

0.53

ungo

0.52

 lead

0.48

κ

0.47

pul

0.46

клад

0.46

 chief

0.46

ke

0.46

תו

0.46

Activations Density 0.326%

punctuation marks and formatting characters used in programming or markup languages

No Comments

No Known Activations