INDEX

Explanations

terms related to various forms of structures and systems in society

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

 houſe

-0.59

 fubject

-0.58

 kaarangay

-0.58

naies

-0.57

rady

-0.54

 singola

-0.54

 fumée

-0.54

 picado

-0.54

 ſmall

-0.53

 couvercle

-0.53

POSITIVE LOGITS

localScale

0.70

CloseOperation

0.66

thme

0.65

(")");

0.63

Personendaten

0.63

 unknownFields

0.61

logenetic

0.61

nological

0.60

}{*}{}

0.60

üglich

0.59

Activations Density 0.767%

terms related to various forms of structures and systems in society

No Comments

No Known Activations