INDEX

Explanations

structured data and key-value pairs in a dataset

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

house

-0.47

AGU

-0.47

우스

-0.46

 House

-0.44

 house

-0.43

Fprintf

-0.43

hane

-0.42

khana

-0.41

Adv

-0.39

 spirit

-0.39

POSITIVE LOGITS

 Roskov

0.89

MemoryWarning

0.83

SourceChecksum

0.79

IndentedString

0.77



0.76

seamnă

0.73

GraphicsUnit

0.73

runApp

0.71

VersionUID

0.69

UserScript

0.69

Activations Density 0.957%

structured data and key-value pairs in a dataset

No Comments

No Known Activations