INDEX

Explanations

words frequently used in how-to instructions and explanations

oai_token-act-pair · gemini-2.0-flash

technical instructions

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

StoryboardSegue

-0.79

WriteBarrier

-0.78

 CreateTagHelper

-0.78

windowFixed

-0.73

 defaultstate

-0.68

tagHelperRunner

-0.66

IntoConstraints

-0.63

utilisons

-0.62

 <>",

-0.60

fjspx

-0.56

POSITIVE LOGITS

toplankton

0.53

 onCreateView

0.47

AfterClass

0.47

Mqtt

0.45

gridad

0.45

 balle

0.44

Dabei

0.43

 erosion

0.42

 fenders

0.42

locus

0.42

Activations Density 19.299%

words frequently used in how-to instructions and explanations

technical instructions

No Comments

No Known Activations