INDEX

Explanations

references to significant points or key insights

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

"point"

np_acts-logits-general · gemini-2.0-flash

point of

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

 HasFactory

-0.82

 SafeMath

-0.66

 DriverManager

-0.65

 initComponents

-0.64

 OFDb

-0.64

 فريبيس

-0.63

 مشين

-0.63

ercito

-0.61

ChildScrollView

-0.61

httphttps

-0.60

POSITIVE LOGITS

 POINT

1.56

 point

1.50

 Point

1.45

POINT

1.38

point

1.38

 points

1.37

Point

1.29

points

1.25

 Points

1.25

 POINTS

1.24

Activations Density 0.130%

references to significant points or key insights

"point"

point of

No Comments

No Known Activations

references to significant points or key insights

"point"

point of

No Comments

No Known Activations