INDEX

Explanations

technical terms and values related to measurements and data analysis

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.66

RTEE

-0.65

Diweddarwch

-0.58

StoryboardSegue

-0.57

MLLoader

-0.56

GTCX

-0.53

NameInMap

-0.53

 Autorizaciones

-0.52

postIndex

-0.52

AddTagHelper

-0.52

POSITIVE LOGITS

 value

0.53

 values

0.48

 calculation

0.47

 measurement

0.47

 estimation

0.45

 percentage

0.45

ostasis

0.44

 amount

0.44

 ratio

0.43

 anorexia

0.43

Activations Density 0.148%

technical terms and values related to measurements and data analysis

No Comments

No Known Activations

technical terms and values related to measurements and data analysis

No Comments

No Known Activations