INDEX

Explanations

significant phrases and descriptions that denote importance or relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

expandindo

-0.91

RefNanny

-0.63

ImageContext

-0.61



-0.59

PerformLayout

-0.58

providedIn

-0.56

richTextPanel

-0.54

lapsingToolbar

-0.54

CreateMap

-0.54

 yourselves

-0.53

POSITIVE LOGITS

aim

0.69

 reason

0.67

 thing

0.66

 goal

0.66

 biggest

0.64

AxisAlignment

0.62

 question

0.62

iastes

0.61

 major

0.58

 main

0.58

Activations Density 0.287%

significant phrases and descriptions that denote importance or relevance

No Comments

No Known Activations