INDEX

Explanations

references to masks in manufacturing or processing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 للاسماء

-0.61

ี่ยม

-0.59

fromUtf

-0.58

bootstrapcdn

-0.54

tetur

-0.52

 hoek

-0.51

StoryboardSegue

-0.51

 preved

-0.50

PostInfinity

-0.49

erry

-0.49

POSITIVE LOGITS

 mask

4.59

 masks

4.15

 Mask

4.07

mask

3.95

Mask

3.78

 MASK

3.72

 Masks

3.72

masks

3.43

Masks

3.24

 masked

3.04

Activations Density 0.060%

references to masks in manufacturing or processing contexts

No Comments

No Known Activations