INDEX

Explanations

phrases that highlight advantages and key differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

脚注の使い方

-0.76

 TextAppearance

-0.67

 AttributeSet

-0.63

endpush

-0.62

évaluateur

-0.61

 MonoBehaviour

-0.61

PyExc

-0.60

expandindo

-0.59

 Wikimedijinoj

-0.59

 estekak

-0.58

POSITIVE LOGITS

 characteristics

0.65

 advantages

0.64

 Features

0.61

 features

0.59

 Advantages

0.58

 característica

0.58

 Characteristics

0.57

 drawbacks

0.57

 feature

0.56

Advantages

0.56

Activations Density 0.477%

phrases that highlight advantages and key differences

No Comments

No Known Activations