INDEX

Explanations

the prepositions used frequently 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

 BoxFit

-0.91

 Ferns

-0.76

ArgsConstructor

-0.75

sym

-0.74

unikasi

-0.74

 Keene

-0.73

uría

-0.73

^(@)

-0.73

 Völ

-0.73

Flas

-0.73

POSITIVE LOGITS

Comments

0.50

0.48

<eos>

0.47

↵↵

0.47

 Barrios

0.47

uslar

0.45

 follows

0.45

ⓧ

0.44

ing

0.44

Follow

0.44

Activations Density 0.004%

the prepositions used frequently in the text

No Comments

No Known Activations