INDEX

Explanations

words related to legal proceedings and judgements, especially disbarment

oai_token-act-pair · gemini-2.0-flash

dis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

dis

-2.73

Dis

-2.44

Dis

-2.39

dis

-2.38

DIS

-1.96

DIS

-1.86

 diss

-1.24

 dise

-1.16

 disp

-1.14

 Dism

-1.12

POSITIVE LOGITS

 Crusade

0.54

 Italijani

0.53

 bacio

0.52

 inning

0.50

 abbraccio

0.50

ایج

0.49

ernoo

0.49

 Kers

0.49

 Kimmel

0.48

 halves

0.47

Activations Density 16.603%

words related to legal proceedings and judgements, especially disbarment

dis

No Comments

No Known Activations