INDEX

Explanations

programming constructs related to logical checks and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

deka

-0.49

 mages

-0.47

 فريبيس

-0.46

 Chama

-0.46

Kjelder

-0.45

 Cæsar

-0.45

 sparring

-0.45

 ObjectMapper

-0.44

 charting

-0.44

ixote

-0.44

POSITIVE LOGITS

elif

0.78

livejournal

0.75

tonode

0.70

aarrggbb

0.64

Према

0.61

 kaarangay

0.60

>`;

0.60

if

0.60

يميديا

0.59

 према

0.58

Activations Density 0.233%

programming constructs related to logical checks and conditions

No Comments

No Known Activations