INDEX

Explanations

names of individuals and their relevant attributes or actions

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

GEBURTSDATUM

-0.65

eaway

-0.62

eaways

-0.62

Rüyada

-0.61

EndGlobalSection

-0.59

isca

-0.58

olv

-0.58

 kasarigan

-0.58

 daya

-0.58

 réguli

-0.57

POSITIVE LOGITS

’

1.07

1.02

 himſelf

0.76

 zufolge

0.67

 doubtnut

0.63

 raiſ

0.63

 myſelf

0.62

 uſed

0.61

ův

0.61

 fometimes

0.60

Activations Density 0.302%

names of individuals and their relevant attributes or actions

No Comments

No Known Activations