INDEX

Explanations

connections between different components and their effects

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

Follows punctuation marks or symbols

np_acts-logits-general · gemini-2.0-flash

start of sentences or clauses

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

-------------</

-0.68

 featuring

-0.61

ONAUT

-0.59

 Utilizing

-0.59

تقاوى

-0.56

sidemargin

-0.55

tagHelperRunner

-0.55

englisch

-0.55

ⓧ

-0.55

IUrlHelper

-0.54

POSITIVE LOGITS

Moreover

0.64

fortunately

0.64

 Undoubtedly

0.64

 undoubtedly

0.63

 Allí

0.62

 Ведь

0.61

 Inoltre

0.61

Among

0.60

 Gleichzeitig

0.59

Parcelize

0.59

Activations Density 0.134%

connections between different components and their effects

Follows punctuation marks or symbols

start of sentences or clauses

No Comments

No Known Activations