INDEX

Explanations

words and phrases in legal documents pertaining to court cases

oai_token-act-pair · gemini-2.0-flash

document structure markers

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.43

 Monfieur

-1.42

 themſelves

-1.41

 Majefty

-1.30

 ―――――

-1.28

 ་་

-1.27

 Shakspeare

-1.25

 itſelf

-1.24

 myſelf

-1.22

 doubtnut

-1.20

POSITIVE LOGITS

↵

0.69

0.62

0.55

0.52

0.50

</h2>

0.50

0.49

 trigo

0.49

0.48

Activations Density 1.494%

words and phrases in legal documents pertaining to court cases

document structure markers

No Comments

No Known Activations