INDEX

Explanations

references to patterns and pattern recognition concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

!("{

-0.84

 doPost

-0.66

AntiForgeryToken

-0.64

})

-0.63

SpringRunner

-0.63

outchouc

-0.63

CURLOPT

-0.62

andere

-0.62

jsonp

-0.62

 noqa

-0.62

POSITIVE LOGITS

 patterns

1.45

 Patterns

1.32

Patterns

1.28

 pattern

1.19

patterns

1.17

 PATTERN

1.12

 Pattern

1.07

pattern

0.97

Pattern

0.94

 patrones

0.87

Activations Density 0.124%

references to patterns and pattern recognition concepts

No Comments

No Known Activations