INDEX

Explanations

sentences asking for opinions of groups of people

oai_token-act-pair · gemini-2.0-flash

gibberish code

np_token-act-pair-logits · gemini-2.0-flash

quotations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

IRM

-0.51

komme

-0.49

 thought

-0.46

isOk

-0.46

 Suffer

-0.44

 structure

-0.43

structure

-0.42

gus

-0.42

 Thought

-0.41

 patron

-0.41

POSITIVE LOGITS

 ModelExpression

0.82

 kaarangay

0.69

CPtr

0.68

setVerticalGroup

0.67

Datuak

0.66

elemField

0.66

devamını

0.65

AddTagHelper

0.64

})`

0.63

'{@

0.63

Activations Density 2.730%

sentences asking for opinions of groups of people

gibberish code

quotations

No Comments

No Known Activations