INDEX

Explanations

the string "Tar"

oai_token-act-pair · gemini-2.0-flash

tokens related to the word "Tar"

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

Tar

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

حياته

-0.57

styleUrls

-0.56

 stay

-0.50

EditorBrowsable

-0.50

 retrait

-0.49

richTextPanel

-0.48

 चीज़ों

-0.46

 Stays

-0.45

ondes

-0.45

 lipat

-0.45

POSITIVE LOGITS

 AssemblyVersion

0.69

GEBURTS

0.64

 IBOutlet

0.57

acu

0.57

 أعلام

0.56

awaiter

0.56

 consultato

0.51

openSession

0.50

 Kana

0.50

 onCreateView

0.49

Activations Density 0.309%

the string "Tar"

tokens related to the word "Tar"

Tar

No Comments

No Known Activations