INDEX

Explanations

positive descriptions of a process.

oai_token-act-pair · gemini-2.0-flash

Simplicity and ease

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 simple

-0.56

Simple

-0.55

\{\\

-0.54

 simplicity

-0.52

 Simple

-0.52

simple

-0.50

 SIMPLE

-0.49

jc

-0.47

SharedCtor

-0.46

}),

-0.45

POSITIVE LOGITS

adaptiveStyles

0.71

 umane

0.70

WithMany

0.63

 ModelExpression

0.63

usercontent

0.60

 étoit

0.59

principalColumn

0.59

 NDEBUG

0.57

 user

0.56

FormTagHelper

0.56

Activations Density 3.939%

positive descriptions of a process.

Simplicity and ease

No Comments

No Known Activations