INDEX

Explanations

words related to moving things around, or changing code in many ways while debugging

oai_token-act-pair · gemini-2.0-flash

rearrange

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Préférences

-0.63

TargetException

-0.62

 referenties

-0.61

 AssemblyCompany

-0.60

ReusableCell

-0.60

HostException

-0.59

RUnlock

-0.59

SourceChecksum

-0.57

 Majefty

-0.57

giveness

-0.57

POSITIVE LOGITS

 rearrangement

0.90

 rearranged

0.80

 rearrange

0.80

 rearranging

0.69

re

0.68

 shuffled

0.68

 arrangement

0.67

 shuffling

0.66

 shuffle

0.64

 move

0.63

Activations Density 1.353%

words related to moving things around, or changing code in many ways while debugging

rearrange

No Comments

No Known Activations