INDEX

Explanations

specific measurements and dimensions related to objects

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

different types or sizes

np_acts-logits-general · gemini-2.0-flash

various and particular descriptors

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

Personendaten

-1.02

parsedMessage

-0.87

 HasFactory

-0.80

BeginContext

-0.78



-0.76

Билгалдахарш

-0.74

 &___

-0.73

ResponseWriter

-0.71

 houſe

-0.71

帖最后由

-0.70

POSITIVE LOGITS

 various

0.45

 bleek

0.42

 suitable

0.42

 Various

0.41

니메이션

0.41

gin

0.40

 tema

0.40

#{

0.40

不通

0.40

 moderate

0.39

Activations Density 0.410%

specific measurements and dimensions related to objects

different types or sizes

various and particular descriptors

No Comments

No Known Activations