INDEX

Explanations

repeated sequences or patterns in the text

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

Code snippets or configuration text

np_acts-logits-general · gemini-2.0-flash

code parsing and manipulation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.56

饋

-0.55

DataAnnotations

-0.54

StoryboardSegue

-0.53

Zip

-0.53

sī

-0.51

 Quad

-0.51

Quad

-0.51

atosis

-0.50

+#+#

-0.49

POSITIVE LOGITS

InjectAttribute

0.68

MLLoader

0.60

 unknownFields

0.55

Skocz

0.54

findpost

0.53

Personensuche

0.51

}}]{

0.50

)':

0.49

 Baillargeon

0.49

nterior

0.48

Activations Density 0.099%

repeated sequences or patterns in the text

Code snippets or configuration text

code parsing and manipulation

No Comments

No Known Activations