INDEX

Explanations

programming-related terminology and commands

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

 noDo

-0.62

RenderAtEndOf

-0.55

transQ

-0.54

Composable

-0.52

 uska

-0.50

véni

-0.49

TypedDataSet

-0.49

InSection

-0.48

 مرئيه

-0.48

 aVar

-0.48

POSITIVE LOGITS

npmjs

0.42

npm

0.38

jsii

0.38

yarnpkg

0.38

NewUrlParser

0.35

npm

0.35

onatos

0.34

 React

0.33

React

0.33

 BigNumberish

0.33

Activations Density 0.019%

programming-related terminology and commands

No Comments

No Known Activations