INDEX

Explanations

programming-related syntax and function definitions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lengkap

-0.43

Slu

-0.42

 ENTR

-0.41

inkt

-0.41

 diverso

-0.41

ameran

-0.41

 general

-0.40

 quelconque

-0.40

 riêng

-0.40

eraus

-0.40

POSITIVE LOGITS

 nakalista

0.82

)__

0.69

Попис

0.63

'{@

0.62

ِّف

0.61

IntoConstraints

0.61

__*/

0.61

 {}));

0.59

__

0.58

GPC

0.58

Activations Density 0.098%

programming-related syntax and function definitions

No Comments

No Known Activations