INDEX

Explanations

technical and analytical terms related to research findings and methodologies

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

rungsseite

-1.35

tagHelperRunner

-1.13

AndEndTag

-1.08

SharedDtor

-1.07

niſſe

-1.07

OGND

-1.05

 Geſch

-1.00

 Geiſt

-1.00

MessageTagHelper

-1.00

EDEFAULT

-1.00

POSITIVE LOGITS

</h3>

0.46

</h2>

0.44

</h4>

0.40

0.39

</strong>

0.39

</b>

0.38

0.36

</u>

0.35

Activations Density 0.220%

technical and analytical terms related to research findings and methodologies

No Comments

No Known Activations