INDEX

Explanations

repeated phrases or terms across various contexts or instances

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

)’

-0.48

ויות

-0.45

новременно

-0.43

gación

-0.42

WAUKEE

-0.40

 alternates

-0.40

 alternate

-0.40

 […]

-0.40

 train

-0.39

 Allen

-0.39

POSITIVE LOGITS

0.81

 EconPapers

0.72



0.69

Geplaatst

0.66

 zoveel

0.65

ConstraintMaker

0.65

limsy

0.63

istoitu

0.62

 <=",

0.62

 élas

0.61

Activations Density 0.097%

repeated phrases or terms across various contexts or instances

No Comments

No Known Activations