INDEX

Explanations

legal jargon and references to legal codes.

oai_token-act-pair · gemini-2.0-flash

technical or legal terms

np_token-act-pair-logits · gpt-4o-mini

formal writing and citations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.75

abaret

-0.39

发表于

-0.38

tania

-0.37

Upgradeable

-0.36

mbros

-0.36

btree

-0.35

 Numerology

-0.34

はじめに

-0.34

וקה

-0.34

POSITIVE LOGITS

 propOrder

0.56

UnsafeEnabled

0.49

 AspNetCore

0.49

MemoryWarning

0.48

ⓧ

0.47

TagMode

0.46

windowFixed

0.44

BagLayout

0.43

rungsseite

0.43

 contextLoads

0.43

Activations Density 14.688%

legal jargon and references to legal codes.

technical or legal terms

formal writing and citations

No Comments

No Known Activations