INDEX

Explanations

codes or numerical representations typically used in scientific or technical contexts

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

 blanches

-0.61

وردار

-0.55

 Farina

-0.53

ômico

-0.51

↵↵

-0.51

↵↵↵

-0.49

Джерела

-0.49

 mivel

-0.49

helves

-0.47

messer

-0.47

POSITIVE LOGITS

+#+#

0.96

LookAnd

0.83

########.

0.77

ValueGenerated

0.76

__*/

0.76

 &___

0.73

@"/

0.72

 WaitForSeconds

0.72

ollectionView

0.70

PhysRev

0.69

Activations Density 0.391%

codes or numerical representations typically used in scientific or technical contexts

No Comments

No Known Activations