INDEX

Explanations

terms related to implied warranties and contractual obligations

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

 utafitiHapana

-0.72

 nakalista

-0.70

 Breen

-0.68

endpush

-0.67

numbered

-0.67

MultipartFile

-0.65

Waga

-0.65

gogo

-0.63

 irregularly

-0.62

andaag

-0.62

POSITIVE LOGITS

 implied

1.63

 IMPLIED

1.52

 implicit

1.36

 implicitly

1.28

 imply

1.25

 implication

1.19

 Implicit

1.15

 implies

1.14

 implying

1.11

implicit

1.09

Activations Density 0.349%

terms related to implied warranties and contractual obligations

No Comments

No Known Activations