INDEX

Explanations

scientific and statistical terms related to performance metrics and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ViewFeatures

-0.68

InstanceState

-0.62

;"></

-0.62

*/;

-0.59

 />);

-0.58

']))

-0.52

ErrorListener

-0.51

']->

-0.50

setu

-0.50

POSITIVE LOGITS

TagMode

0.74

 Metacritic

0.71

itability

0.70

 percentage

0.69

sidemargin

0.69

 ratio

0.68

percentage

0.68

PullParser

0.67

 MessageBoxIcon

0.66

 Ratio

0.66

Activations Density 1.132%

scientific and statistical terms related to performance metrics and evaluation

No Comments

No Known Activations