INDEX

Explanations

terms related to boundaries, limits, and definitions within various contexts

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

limits or boundaries

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

Background

-0.49

 boire

-0.49

myspace

-0.48

IVIA

-0.48

BACKGROUND

-0.45

 plomo

-0.45

 ausser

-0.45

 बे

-0.44

 outright

-0.43

RESUMEN

-0.43

POSITIVE LOGITS

SerializedSize

0.96

NameInMap

0.94

IndentedString

0.90

Tikang

0.88

 Савезне

0.81

IntoConstraints

0.79

 NSCoder

0.79

richTextPanel

0.78

TextHelper

0.78

 AssemblyCulture

0.77

Activations Density 0.436%

terms related to boundaries, limits, and definitions within various contexts

followed by prepositions

limits or boundaries

No Comments

No Known Activations