INDEX

Explanations

terms related to software licensing and legal disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

putExtra

-0.47

<eos>

-0.46

]=>

-0.46

 cruzar

-0.44

 CallOverrides

-0.41

zugehen

-0.40

 post

-0.40

Has

-0.38

 fake

-0.38

inguém

-0.38

POSITIVE LOGITS

 Wallflower

0.72

WriteTagHelper

0.70

MessageOf

0.69

 Software

0.67

AsUp

0.65

 redistribution

0.64

withstanding

0.62

 MERCHANTABILITY

0.61

 Redist

0.60

Software

0.60

Activations Density 0.337%

terms related to software licensing and legal disclaimers

No Comments

No Known Activations