INDEX

Explanations

references to legal proceedings and court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ValueStyle

-0.69

verständlich

-0.52

liston

-0.51

cut

-0.51

]^{-

-0.50

 thinner

-0.48

parral

-0.47

am

-0.47

ter

-0.47

 consist

-0.46

POSITIVE LOGITS

Efq

0.83

 Chriftian

0.76

tvguidetime

0.73

 Monfieur

0.72

 Jefus

0.70

 Majefty

0.59

 myſelf

0.59

 Houſe

0.59

CloseOperation

0.57

 ESPECIAL

0.57

Activations Density 0.555%

references to legal proceedings and court cases

No Comments

No Known Activations