INDEX

Explanations

legal language related to disclaimers and warranties

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

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

NotBe

-0.68

 become

-0.59

become

-0.57

 Become

-0.56

 becoming

-0.55

becomes

-0.55

 Becoming

-0.54

 becomes

-0.54

Become

-0.53

becoming

-0.52

POSITIVE LOGITS

 onOptions

0.80

الحياه

0.77

 DOES

0.73

ⓧ

0.72

zzleHttp

0.72

 kasarigan

0.71

ItemBackground

0.70

GEBURTSDATUM

0.70

StoryboardSegue

0.69

 does

0.69

Activations Density 0.515%

legal language related to disclaimers and warranties

No Comments

No Known Activations