INDEX

Explanations

code snippets or syntax related to programming and markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 utafitiHapana

-0.52

mergeFrom

-0.51

❉

-0.50

 kasarigan

-0.47

 realistas

-0.47

くらいで

-0.44

 shivering

-0.44

webElement

-0.44

 cristiana

-0.44

 Barrow

-0.44

POSITIVE LOGITS

 ostavi

0.94

 متعلقه

0.77

 թվական

0.71

neſs

0.70

TokenNameLPAREN

0.70

 Diſ

0.70

 ſta

0.69

 purpoſe

0.68

 للمعارف

0.68

 isNameExpr

0.68

Activations Density 0.083%

code snippets or syntax related to programming and markup languages

No Comments

No Known Activations