INDEX

Explanations

terms related to statistical analysis and model evaluation

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

"Explaining" or "explained"

np_acts-logits-general · gemini-2.0-flash

explaining variation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 lenker

-0.67

 referenties

-0.65

 חיצוניים

-0.64

RegistryLite

-0.59

zzleHttp

-0.58

 Roskov

-0.56

RTCK

-0.55

 comparator

-0.53

 AssemblyTitle

-0.53

تقاوى

-0.53

POSITIVE LOGITS

 explaining

1.02

 explained

1.00

 explain

0.96

 explanation

0.94

 explanatory

0.91

 explains

0.86

 verkla

0.85

 unexplained

0.84

 Explanation

0.83

 explanations

0.82

Activations Density 0.905%

terms related to statistical analysis and model evaluation

"Explaining" or "explained"

explaining variation

No Comments

No Known Activations