INDEX

Explanations

symbol tokens typically used in programming or markup languages

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

homonymie

-0.88

Portály

-0.85

 Wikimedijinoj

-0.83

writeFieldEnd

-0.78

Tikang

-0.76

RegistryLite

-0.76

NameInMap

-0.71

TintMode

-0.70

----</

-0.68

 utafitiHapana

-0.67

POSITIVE LOGITS

0.81

//

0.69

_("

0.65

The

0.65

The

0.62

“

0.59

ofos

0.58

<th>

0.57

“

0.55

Activations Density 0.007%

symbol tokens typically used in programming or markup languages

No Comments

No Known Activations