INDEX

Explanations

numerical values, particularly related to statistics or results

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

OGND

-0.94

 fides

-0.71

 ogen

-0.63

 inversa

-0.63

 taxon

-0.63

Novel

-0.62

 Wray

-0.62

 sanitaire

-0.61

Brainz

-0.61

+#+

-0.60

POSITIVE LOGITS

 tartalomajánló

0.59

GNUC

0.58

oudoune

0.57

 Vikipedi

0.57

YourGuide

0.52

 ExecuteAsync

0.52

̛

0.52

numel

0.52

duled

0.52

WireFormat

0.52

Activations Density 0.127%

numerical values, particularly related to statistics or results

No Comments

No Known Activations