INDEX

Explanations

technical terms related to mechanisms and systems

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

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

XmlAccessType

-0.96

الحياه

-0.74

WithIOException

-0.72

 BoxDecoration

-0.71

 ExecuteAsync

-0.68

+#+#

-0.66

XmlRootElement

-0.66

 chi̍t

-0.65

+:+

-0.64

tvguidetime

-0.63

POSITIVE LOGITS

ts

0.44

 reception

0.44

спу

0.44

贝

0.43

assertNot

0.42

бель

0.42

(((

0.42

BDA

0.41

BI

0.41

rix

0.41

Activations Density 0.461%

technical terms related to mechanisms and systems

No Comments

No Known Activations