INDEX

Explanations

connections or relationships between different entities or concepts

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

Code or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

comparison/conditions

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

 axles

-0.78

 aeration

-0.71

ArgumentParser

-0.69

 Anderson

-0.66

ArrayAdapter

-0.65

 axle

-0.65

 agriculture

-0.65

 ANALYSIS

-0.65

 Analysis

-0.65

 artery

-0.65

POSITIVE LOGITS

 HasFactory

0.60



0.57

humidité

0.55

éclairage

0.53

Intérieur

0.49

épisode

0.49

esterno

0.48

guenos

0.47

extérieur

0.47

 Italijanski

0.46

Activations Density 0.469%

connections or relationships between different entities or concepts

Code or mathematical expressions

comparison/conditions

No Comments

No Known Activations