INDEX

Explanations

mentions of notable features or elements in various 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

 mAdapter

-0.72

 soin

-0.68

sm

-0.68

^=

-0.66

mosis

-0.66

Bises

-0.65

pecha

-0.64

 caseros

-0.64

askins

-0.63

umenical

-0.63

POSITIVE LOGITS

 Highlight

1.20

Highlighted

1.16

 Highlights

1.14

Highlights

1.12

highlights

1.12

 highlight

1.10

 highlights

1.07

Highlight

1.07

highlight

1.01

 highlighting

0.99

Activations Density 0.015%

mentions of notable features or elements in various contexts

No Comments

No Known Activations