INDEX

Explanations

phrases that reference formal communications or statements regarding events or issues

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

arre

-0.52

 insegna

-0.52

 desiderio

-0.47

 finished

-0.45

MultipartFile

-0.45

 cylinders

-0.45

Finished

-0.44

 individuale

-0.44

].

-0.44

pectiva

-0.43

POSITIVE LOGITS

 consultato

0.64

MLLoader

0.62

 Paglinawan

0.60

derabad

0.59

 Gazetteer

0.59

lihood

0.58

 Wikimedijinoj

0.58

TintMode

0.57

CrossRef

0.57

 spake

0.57

Activations Density 0.105%

phrases that reference formal communications or statements regarding events or issues

No Comments

No Known Activations