INDEX

Explanations

phrases related to error messages or account settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Meksiku

-0.88

FormTagHelper

-0.84

audiovisuel

-0.82

PhysRevD

-0.79

Бахар

-0.79

 SwitchCompat

-0.78

ViewImports

-0.74

 فريبيس

-0.73

исленность

-0.73

HasForeignKey

-0.72

POSITIVE LOGITS

ⓧ

0.99

 مرئيه

0.62

ѓ

0.61

0.56

حياته

0.56

0.54

НИК

0.54

 randomised

0.52

 թվական

0.52

Activations Density 0.118%

phrases related to error messages or account settings

No Comments

No Known Activations