INDEX

Explanations

statistical terms and concepts related to logarithmic transformations and models

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

AndEndTag

-0.43

RTDA

-0.38

hyrchwyd

-0.36

Localized

-0.36

ParallelGroup

-0.34

:+:

-0.33

 попере

-0.33

 vVar

-0.33

IntoConstraints

-0.33

 pluri

-0.32

POSITIVE LOGITS

 EconPapers

0.47

Datuak

0.46

LikeLike

0.45

الدراسه

0.45

 AssemblyTitle

0.45

 فريبيس

0.44

esModule

0.43

 يتيمه

0.43

httphttps

0.43

AnimationsModule

0.41

Activations Density 0.405%

statistical terms and concepts related to logarithmic transformations and models

No Comments

No Known Activations