INDEX

Explanations

floating point numbers starting with "0.2", "0.5", or "0.7", and also finds the micro symbol for micrograms

oai_token-act-pair · gemini-2.0-flash

numeric values and programming related terms

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

5

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

Negative Logits

 Infórmanos

-0.47

Occurred

-0.47

MethodManager

-0.46

 ModelExpression

-0.44

ințe

-0.44

Wyn

-0.44

PhysRevD

-0.43

 Eight

-0.42

ients

-0.42

سطس

-0.40

POSITIVE LOGITS

0.96

pě

0.68

__':

0.65

５

0.64

mainloop

0.63

Зноскі

0.61

 AspNetCore

0.61

𝟱

0.59

NegativeButton

0.57

portál

0.57

Activations Density 2.123%

floating point numbers starting with "0.2", "0.5", or "0.7", and also finds the micro symbol for micrograms

numeric values and programming related terms

5

No Known Activations