INDEX

Explanations

references to "point" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 HasFactory

-0.88

ChildScrollView

-0.84

 umani

-0.76

(!__

-0.73

ercito

-0.73

 DELLE

-0.72

 Theſe

-0.72

 OFDb

-0.71

 onCancelled

-0.70

 MainAxisSize

-0.69

POSITIVE LOGITS

 POINT

1.66

 point

1.56

 points

1.52

 Point

1.51

point

1.50

POINT

1.49

 Points

1.38

 POINTS

1.38

Point

1.38

points

1.36

Activations Density 0.086%

references to "point" in various contexts

No Comments

No Known Activations