INDEX

Explanations

terms related to mathematical variables and expressions

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

PROTOBUF

-0.73

 ла

-0.66

vix

-0.65

-0.64

าท

-0.64

равда

-0.63

bush

-0.62

Mes

-0.61

不可

-0.60

“

-0.60

POSITIVE LOGITS

 okuyayım

1.06

WriteTagHelper

0.91

Rhestr

0.88

Rujuakan

0.87

ScopeManager

0.86

WriteBarrier

0.86

 PropTypes

0.85

 EnglishChoose

0.83

 initComponents

0.83

 Alam

0.82

Activations Density 0.217%

terms related to mathematical variables and expressions

No Comments

No Known Activations