INDEX

Explanations

second-person pronouns and auxiliary verbs

oai_token-act-pair · gemini-2.0-flash

modal verbs and references to potential actions

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

You

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تانيه

-0.51

 devons

-0.47

受

-0.46

ClientRect

-0.46

alış

-0.43

 salade

-0.42

mini

-0.41

 onBind

-0.41

:=

-0.40

履

-0.40

POSITIVE LOGITS

IsContent

0.96

 الرياضيه

0.91

IntoConstraints

0.80

 noDo

0.79

 autorytatywna

0.78

 lenker

0.76

could

0.76

 Could

0.75

 could

0.73

protoimpl

0.73

Activations Density 0.821%

second-person pronouns and auxiliary verbs

modal verbs and references to potential actions

You

No Comments

No Known Activations