INDEX

Explanations

proper nouns, particularly names and titles related to legal 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

 EconPapers

-1.25

tagHelperRunner

-1.13

 Normdatei

-1.10

 nahilalakip

-0.99

GEBURTSDATUM

-0.98

ſelf

-0.97

ſelves

-0.97

FunctionFlags

-0.97

 ujednoznacz

-0.95

Hentet

-0.93

POSITIVE LOGITS

↵

0.88

</em>

0.78

TagMode

0.72

</i>

0.64

</h2>

0.58

\\

0.52

↵↵

0.51

0.47

</h5>

0.47

Activations Density 0.178%

proper nouns, particularly names and titles related to legal contexts

No Comments

No Known Activations

proper nouns, particularly names and titles related to legal contexts

No Comments

No Known Activations