INDEX

Explanations

programming terminology related to dynamic component creation and manipulation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-1.12

TargetException

-1.08

LookAnd

-1.06

BufferException

-1.05

Personensuche

-0.98

Efq

-0.97

jsii

-0.96

出版年

-0.96

Билгалдахарш

-0.96

DebuggerNonUser

-0.95

POSITIVE LOGITS

0.50

0.47

0.46

 instance

0.46

0.44

ль

0.44

 aware

0.43

 belieb

0.42

Activations Density 2.144%

programming terminology related to dynamic component creation and manipulation

No Comments

No Known Activations