INDEX

Explanations

technical terms and phrases related to processes or methods in various fields, particularly those involving explanation or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Underline

-0.44

 وعد

-0.41

]}>

-0.40

}{{\

-0.40

 tros

-0.40

,‎

-0.40

agrid

-0.39

 numberOfRows

-0.38

}`}>

-0.38

baj

-0.38

POSITIVE LOGITS

InjectAttribute

0.73

XmlAccessType

0.71

oredCriteria

0.68

SequentialGroup

0.66

RegressionTest

0.65

Viited

0.65

InstanceState

0.61

 Amity

0.59

 NSCoder

0.57

contentLoaded

0.56

Activations Density 0.496%

technical terms and phrases related to processes or methods in various fields, particularly those involving explanation or evaluation

No Comments

No Known Activations