INDEX

Explanations

phrases indicating suitability and ideal conditions for various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.75

onAttach

-0.70

GrantedAuthority

-0.65

scriptcase

-0.63

RegistryLite

-0.63

parsedMessage

-0.63

ecraft

-0.60

aarrggbb

-0.59

quiel

-0.59

MLLoader

-0.59

POSITIVE LOGITS

 geeignet

0.82

 ideal

0.77

 suited

0.68

atschappij

0.68

 idéal

0.66

Dux

0.65

ideal

0.65

 Ideal

0.64

 sekali

0.62

 Gelegenheit

0.62

Activations Density 0.166%

phrases indicating suitability and ideal conditions for various contexts

No Comments

No Known Activations