INDEX

Explanations

phrases like "by the way", "notice that", and words that express thought

oai_token-act-pair · gemini-2.0-flash

Giving instruction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 متعلقه

-0.62

 AssemblyProduct

-0.62

complexType

-0.62

KEYCODE

-0.58

tschaft

-0.56

InjectAttribute

-0.54

]`

-0.54

rían

-0.54

Legături

-0.53

IInterface

-0.53

POSITIVE LOGITS

 note

0.64

Note

0.61

note

0.60

 Note

0.59

aarrggbb

0.55

 AssemblyCulture

0.54

banda

0.54

!*\

0.50

Crop

0.49

 carri

0.48

Activations Density 1.668%

phrases like "by the way", "notice that", and words that express thought

Giving instruction

No Comments

No Known Activations