INDEX

Explanations

empty lines

oai_token-act-pair · gemini-2.0-flash

programming function names

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

Code and unusual words

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

Not in Any Lists

No Comments

Negative Logits

rhosis

-0.51

 SwitchCompat

-0.49

drawSprites

-0.49

omorph

-0.46

matsu

-0.45

mirante

-0.45

 године

-0.45

insegna

-0.45

googleapis

-0.44

mingen

-0.44

POSITIVE LOGITS

ViewFeatures

0.67

UnitTesting

0.60

StoreMessageInfo

0.59

Hentet

0.55

 resourceCulture

0.52

UIControlState

0.52

Clik

0.51

Diweddarwch

0.50

цездатний

0.50

 Mehdi

0.50

Activations Density 0.397%

empty lines

programming function names

Code and unusual words

No Comments

No Known Activations