INDEX

Explanations

references to units of measurement or energy

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 GenerationType

-0.67

 للمعارف

-0.67

lwjgl

-0.64

Демографія

-0.59

-0.58

ChildScrollView

-0.57

([^

-0.57

Blas

-0.56

 Conclu

-0.56

 Kraw

-0.56

POSITIVE LOGITS

 unit

3.95

 units

3.62

 Unit

3.57

unit

3.39

 Units

3.33

Unit

3.29

 UNIT

3.21

units

3.10

Units

2.97

 UNITS

2.93

Activations Density 0.048%

references to units of measurement or energy

No Comments

No Known Activations