INDEX

Explanations

references to test-related terminology or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Autoritní

-1.01

----</

-0.78

 TestBed

-0.70

 ſever

-0.70

loài

-0.70

ſtra

-0.69

ſſed

-0.69

BibitemShut

-0.67

ruptedException

-0.67

namefont

-0.66

POSITIVE LOGITS

2.90

2.67

2.61

2.28

getT

1.67

ｔ

1.49

ت

1.35

т

1.31

𝘁

1.24

Т

1.23

Activations Density 0.564%

references to test-related terminology or structures

No Comments

No Known Activations