INDEX

Explanations

programming constructs related to assignments and return statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

jooq

-0.50

AnchorStyles

-0.45

 setting

-0.45

SharedCtor

-0.45

–

-0.45

-0.43

 disambiguazione

-0.43

 jLabel

-0.43

 prise

-0.39

 plata

-0.39

POSITIVE LOGITS

$_"

0.81

 Wicidata

0.76

سطس

0.74

NUMX

0.73

YourGuide

0.72

ſelves

0.72

 staden

0.70

 purpoſe

0.69

berdayakan

0.69

 ―――――

0.69

Activations Density 0.161%

programming constructs related to assignments and return statements

No Comments

No Known Activations