INDEX

Explanations

references to specific technical specifications or criteria

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

Follows punctuation, "Q", or conjunctions

np_acts-logits-general · gemini-2.0-flash

Q/A format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

OGND

-0.95

tagHelperRunner

-0.76

Personensuche

-0.76

 purpoſe

-0.72

=()=>{

-0.71

ⓧ

-0.70

₂+

-0.70

 disambiguazione

-0.69

 AdapterView

-0.68

 myſelf

-0.67

POSITIVE LOGITS

0.52

 NSCoder

0.48

 endwhile

0.47

 خارجية

0.45

0.44

+#+

0.43

 Dritten

0.43

 accordingly

0.41

 urbano

0.41

 admi

0.40

Activations Density 0.050%

references to specific technical specifications or criteria

Follows punctuation, "Q", or conjunctions

Q/A format

No Comments

No Known Activations