INDEX

Explanations

references to quantitative data and numeric parameters

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

followed by a negation

np_acts-logits-general · gemini-2.0-flash

better change, all unanimously, wrong target

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

omg

-0.59

enschaften

-0.54

Искәрмәләр

-0.54

apimachinery

-0.52

Omg

-0.50

kově

-0.49

सन्दर्भ

-0.49

typeorm

-0.49

OVERALL

-0.48

뻐

-0.48

POSITIVE LOGITS

GEBURTSDATUM

0.67

+:+

0.64

SourceChecksum

0.64

AddTagHelper

0.63

 оригіналу

0.63

 oprot

0.60

帖最后由

0.60

 damn

0.59

styleType

0.58

 hyphen

0.57

Activations Density 0.554%

references to quantitative data and numeric parameters

followed by a negation

better change, all unanimously, wrong target

No Comments

No Known Activations