INDEX

Explanations

a hodgepodge of seemingly unrelated terms.

oai_token-act-pair · gemini-2.0-flash

say "one"

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

Negative Logits

two

-1.27

Two

-1.22

two

-1.20

Two

-1.19

TWO

-1.16

 deux

-1.10

Three

-1.10

TWO

-1.09

II

-1.08

 three

-1.05

POSITIVE LOGITS

原始内容存档于

0.69

 MessageBoxIcon

0.66

 insuffisamment

0.60

ToolStrip

0.60

WriteAttribute

0.58

IntoConstraints

0.57

ViewImports

0.56

 BoxFit

0.55

BufferException

0.55

 GenerationType

0.55

Activations Density 4.025%

a hodgepodge of seemingly unrelated terms.

say "one"

No Known Activations