INDEX

Explanations

statements that assess the significance or relevance of various legal and medical arguments

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

Adjectives followed by prepositions

np_acts-logits-general · gemini-2.0-flash

importance and emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GEBURTSDATUM

-1.08

StoryboardSegue

-0.94

 صوتيه

-0.82

StructEnd

-0.82

 Roskov

-0.81

:✨

-0.78

ImageContext

-0.78

 ModelExpression

-0.77

expandindo

-0.76

цездатний

-0.75

POSITIVE LOGITS

 particularly

0.82

 especially

0.77

particularly

0.67

 Particularly

0.62

ticularly

0.61

 Especially

0.59

especially

0.58

Especially

0.54

 zwłaszcza

0.54

 insbesondere

0.54

Activations Density 0.587%

statements that assess the significance or relevance of various legal and medical arguments

Adjectives followed by prepositions

importance and emphasis

No Comments

No Known Activations