INDEX

Explanations

titles and designations of people, sometimes related to legal issues

oai_token-act-pair · gemini-2.0-flash

names

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Efq

-0.95

ſelves

-0.82

 Forumite

-0.81

 itſelf

-0.79

 myſelf

-0.77

ſelf

-0.76

 Jefus

-0.76

^(@)

-0.75

setVerticalGroup

-0.73

WithIOException

-0.70

POSITIVE LOGITS

 Cheryl

0.68

 Diane

0.66

 Gail

0.65

 Dennis

0.65

 Trevor

0.64

 Brian

0.63

 Dustin

0.63

 Greg

0.63

 Elmer

0.63

 Dave

0.62

Activations Density 2.334%

titles and designations of people, sometimes related to legal issues

names

No Comments

No Known Activations