INDEX

Explanations

words related to hypothesis, computer code, and academic writing

oai_token-act-pair · gemini-2.0-flash

example

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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

 onBackPressed

-0.64

 myſelf

-0.59

 pleaſure

-0.57

 neceff

-0.56

 ſch

-0.56

 paff

-0.55

 fune

-0.55

AnchorStyles

-0.54

 perfons

-0.54

 faſt

-0.54

POSITIVE LOGITS

 example

2.20

 examples

2.03

Example

2.00

 Example

1.99

example

1.91

 EXAMPLE

1.86

 Examples

1.84

EXAMPLE

1.83

Examples

1.78

 ejemplo

1.78

Activations Density 3.674%

words related to hypothesis, computer code, and academic writing

example

No Comments

No Known Activations

words related to hypothesis, computer code, and academic writing

example

No Comments

No Known Activations