INDEX

Explanations

technical terms related to software systems and their configurations

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

associated with location or housing

np_acts-logits-general · gemini-2.0-flash

lives in or resided in

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IndentedString

-0.71

ậc

-0.54

rrggbb

-0.52

ByUserId

-0.47

complexType

-0.45

chak

-0.43

érêt

-0.41

sitis

-0.41

პ

-0.40

 niệm

-0.40

POSITIVE LOGITS

 resides

1.10

 housed

0.98

 berada

0.96

 reside

0.95

 residing

0.94

 resided

0.94

อยู่ใน

0.93

 occupying

0.91

 inhabiting

0.89

 located

0.87

Activations Density 0.789%

technical terms related to software systems and their configurations

associated with location or housing

lives in or resided in

No Comments

No Known Activations