INDEX

Explanations

quantities and forms of information related to products and treatments

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

rinfo

-0.67

BeginContext

-0.66

 AppComponent

-0.62

baguna

-0.61

 Locomo

-0.59

enumi

-0.57

 دیکھیے

-0.57

 braking

-0.56

Билгалдахарш

-0.56

RTLD

-0.55

POSITIVE LOGITS

 homemade

0.86

homemade

0.76

 online

0.72

 manual

0.71

DIY

0.69

 Homemade

0.69

 electronic

0.69

 tự

0.68

 traditional

0.66

 outsourced

0.66

Activations Density 0.934%

quantities and forms of information related to products and treatments

No Comments

No Known Activations