INDEX

Explanations

mentions of specific activities or actions related to learning and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

RenderAtEndOf

-0.60

GEBURTSDATUM

-0.54

berdayakan

-0.53

 transfieras

-0.51

ondissement

-0.50

Şi

-0.49

mbitos

-0.48

tagHelperRunner

-0.48

pecabe

-0.47

 terecht

-0.47

POSITIVE LOGITS

 während

0.52

 watching

0.52

 watched

0.47

 durante

0.47

 during

0.46

watched

0.44

 Während

0.44

during

0.43

Während

0.43

watching

0.42

Activations Density 0.505%

mentions of specific activities or actions related to learning and entertainment

No Comments

No Known Activations