INDEX

Explanations

code or programming-related syntax elements within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

httphttps

-0.55

évaluateur

-0.51

 الحره

-0.49

glGen

-0.47

hals

-0.45

θη

-0.45

Nov

-0.44

hind

-0.43

Raphael

-0.43

órmulas

-0.43

POSITIVE LOGITS

webElementXpaths

0.75

AndroidJUnit

0.59

kezik

0.58

Efq

0.58

 gynnwys

0.58

 bosco

0.57

})();

0.56

jalá

0.56

 Diſ

0.55

 fratelli

0.54

Activations Density 0.099%

code or programming-related syntax elements within text

No Comments

No Known Activations