INDEX

Explanations

specific terms and technical language related to legal documents and processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

preceding a state of being

np_acts-logits-general · gemini-2.0-flash

medical research, technical documents, and media

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sizeCache

-0.76

 كومونز

-0.69

 HasFactory

-0.68

richTextPanel

-0.62

orianCalendar

-0.57

BufferException

-0.56

<bos>

-0.56

CodeAttribute

-0.52

indd

-0.51

 beginnetje

-0.51

POSITIVE LOGITS

 itself

0.58

Diweddarwch

0.54

zbęd

0.54

itself

0.53

otras

0.51

noty

0.50

SBATCH

0.50

ρων

0.49

setVerticalGroup

0.47

ERI

0.46

Activations Density 0.892%

specific terms and technical language related to legal documents and processes

preceding a state of being

medical research, technical documents, and media

No Comments

No Known Activations