INDEX

Explanations

text with the words "you," "your," and "my."

oai_token-act-pair · gemini-2.0-flash

possessive pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

пом

-0.49

lo

-0.45

-0.44

-0.42

in

-0.42

on

-0.42

 teus

-0.40

POSITIVE LOGITS

 Majefty

1.17

Efq

1.06

ſelf

1.02

 houſe

1.02

 Jefus

1.00

 pleaſure

0.95

 Monfieur

0.95

 purpoſe

0.93

 Houſe

0.92

Rhestr

0.88

Activations Density 2.688%

text with the words "you," "your," and "my."

possessive pronouns

No Comments

No Known Activations