INDEX

Explanations

terms related to adsorption processes

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

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

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wpi

-0.75

 Audiodateien

-0.68

 métiers

-0.64

#![

-0.59

 Britannia

-0.54

AFTA

-0.53

libur

-0.52

urlopen

-0.52

tpl

-0.52

 velocidades

-0.52

POSITIVE LOGITS

 adsorption

1.27

sorption

1.24

 Adsorption

1.20

 adsor

1.06

 adsorbed

0.95

orption

0.87

 ExecuteAsync

0.85

MessageState

0.84

 isother

0.83

 CreateTagHelper

0.77

Activations Density 0.002%

terms related to adsorption processes

No Comments

No Known Activations