INDEX

Explanations

repeated occurrences of the variable 'i' in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

CloseOperation

-0.83

 ivelany

-0.71

-0.61

ensement

-0.61

 GeoNames

-0.59

ve

-0.57

."],

-0.57

st

-0.57

."),

-0.56

utnik

-0.56

POSITIVE LOGITS

 iVar

0.76

 griega

0.59

 beauté

0.57

droje

0.55

 bénévol

0.53

 maternidade

0.53

am

0.52

 paixão

0.51

rosophila

0.51

 když

0.50

Activations Density 0.208%

repeated occurrences of the variable 'i' in code

No Comments

No Known Activations