INDEX

Explanations

references to "cover" in various contexts

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

"cover" and its variations

np_acts-logits-general · gemini-2.0-flash

cover

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

וויק

-0.60

 Dumont

-0.58

GeoNames

-0.58

</tfoot>

-0.56

Havolalar

-0.56

rlpool

-0.56

ContentAsync

-0.55

makeText

-0.55

 linden

-0.54

(@"%@",

-0.53

POSITIVE LOGITS

tly

1.23

Covers

0.97

 Covers

0.96

COVER

0.90

 ujednoznacz

0.89

 covers

0.86

 COVER

0.86

 Cover

0.79

Cover

0.76

covered

0.71

Activations Density 0.089%

references to "cover" in various contexts

"cover" and its variations

cover

No Comments

No Known Activations