INDEX

Explanations

numerical data or values, particularly in scientific contexts

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

 McCar

-0.56

URING

-0.56

chaub

-0.54

tract

-0.54

-0.53

)|^{

-0.51

ories

-0.51

zulegen

-0.51

ément

-0.50

ền

-0.49

POSITIVE LOGITS

 EconPapers

0.81

bewerken

0.68

protoimpl

0.60

IonicModule

0.59

 himo

0.59

+#+

0.57

LookAnd

0.56

Tembelea

0.55

Cyfeiriadau

0.54

SequentialGroup

0.53

Activations Density 0.050%

numerical data or values, particularly in scientific contexts

No Comments

No Known Activations

numerical data or values, particularly in scientific contexts

No Comments

No Known Activations