INDEX

Explanations

references to "points" or "pointing."

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

 Theſe

-0.85

expandindo

-0.83

 HasFactory

-0.82

ChildScrollView

-0.80

Autoritní

-0.77

 OFDb

-0.74

 فريبيس

-0.74

GraphicsUnit

-0.71

ercito

-0.71

MemoryWarning

-0.71

POSITIVE LOGITS

 POINT

1.64

 point

1.57

 Point

1.51

point

1.50

 points

1.49

POINT

1.45

Point

1.39

points

1.36

 POINTS

1.33

 Pointe

1.31

Activations Density 0.080%

references to "points" or "pointing."

No Comments

No Known Activations