INDEX

Explanations

mentions of wheels and related components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

arXiv

-0.83

 nakalista

-0.78

)++;

-0.72

createNewFile

-0.69

 Gore

-0.66

%+

-0.66

itons

-0.66

Bates

-0.65

Bronnen

-0.64

verez

-0.63

POSITIVE LOGITS

 wheel

3.31

wheel

3.09

 Wheel

3.05

 wheels

3.00

Wheel

2.82

 WHEEL

2.80

wheels

2.69

 Wheels

2.66

WHEEL

2.42

Wheels

2.41

Activations Density 0.050%

mentions of wheels and related components

No Comments

No Known Activations