INDEX

Explanations

calls to action such as looking at or checking something out

oai_token-act-pair · gemini-2.0-flash

pronouns and possessives

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

Calls to action

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

you

-0.75

You

-0.69

you

-0.63

 vous

-0.57

KommentareTeilen

-0.55

You

-0.54

YOU

-0.51

あなたは

-0.50

 você

-0.50

 bạn

-0.50

POSITIVE LOGITS

our

0.97

the

0.93

 their

0.86

my

0.80

 this

0.74

 these

0.70

 previous

0.64

 meille

0.64

 propOrder

0.63

 protoimpl

0.62

Activations Density 5.018%

calls to action such as looking at or checking something out

pronouns and possessives

Calls to action

No Comments

No Known Activations