INDEX

Explanations

references to additional information or conditions that are elaborated in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quila

-0.44

CustomerID

-0.43

 compa

-0.42

-0.41

ztály

-0.41

Bar

-0.41

Tre

-0.40

onaire

-0.39

titudine

-0.39

lindung

-0.38

POSITIVE LOGITS

LookAnd

1.12

 <<<<<<<<<<<<<<

1.06

ViewFeatures

1.05

tagHelperRunner

1.01

SharedCtor

1.00

 مشين

0.99

 AssemblyCulture

0.97

 CreateTagHelper

0.93

NameInMap

0.93

SharedDtor

0.91

Activations Density 0.187%

references to additional information or conditions that are elaborated in the text

No Comments

No Known Activations