INDEX

Explanations

proper nouns and unique identifiers related to various topics

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

OGND

-0.57

 surla

-0.55

 AssemblyTitle

-0.45

ISupport

-0.41

 ujednoznacz

-0.41

RenderAtEndOf

-0.41

CodeAttribute

-0.40

VersionUID

-0.40

styleable

-0.40

Šaltiniai

-0.40

POSITIVE LOGITS

 صوتيه

0.46

Intervention

0.45

onedDateTime

0.44

setFill

0.44

spesies

0.43

episode

0.43

 Theme

0.43

enment

0.43

UserScript

0.42

 dAtA

0.42

Activations Density 1.250%

proper nouns and unique identifiers related to various topics

No Comments

No Known Activations