INDEX

Explanations

specific numeric patterns or sequences in the text

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

fromnode

-0.62

 devoirs

-0.52

 religieuses

-0.52

fhir

-0.48

########.

-0.48

stdc

-0.48

ărul

-0.46

 consommer

-0.46

toro

-0.45

 lucht

-0.45

POSITIVE LOGITS

AccessorTable

0.80

windowFixed

0.69

 newOwner

0.69

BeginContext

0.68

 unknownFields

0.66

rinfo

0.66

RegistryLite

0.65

 initComponents

0.63

 Савезне

0.63

 Roskov

0.63

Activations Density 0.000%

specific numeric patterns or sequences in the text

No Comments

No Known Activations

specific numeric patterns or sequences in the text

No Comments

No Known Activations