INDEX

Explanations

references to publication details and journalistic attribution

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

Follows numbers

np_acts-logits-general · gemini-2.0-flash

numbers and years

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

 nahilalakip

-0.92

icolon

-0.76

 nakalista

-0.76

لينكات

-0.76

íncia

-0.72

AddTagHelper

-0.72

Enllaces

-0.71

)}]{

-0.69

قایناقلار

-0.67

SharedDtor

-0.66

POSITIVE LOGITS

ⓧ

0.51

BindView

0.49

...

0.41

None

0.41

man

0.41

ThroughAttribute

0.41

io

0.40

att

0.40

??

0.39

tom

0.39

Activations Density 0.078%

references to publication details and journalistic attribution

Follows numbers

numbers and years

No Comments

No Known Activations