INDEX

Explanations

regular expressions and code snippets related to parsing or manipulating text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

BeginInit

-0.72

исленность

-0.68

WireFormatLite

-0.64

 <>",

-0.63

󠁴

-0.54

 Certi

-0.53

 elevator

-0.53

 easel

-0.52

RenderAtEndOf

-0.51

 Quay

-0.51

POSITIVE LOGITS

 pattern

1.37

Pattern

1.36

 Pattern

1.34

 regex

1.27

 patterns

1.26

pattern

1.24

 match

1.23

regex

1.20

 Match

1.20

 Patterns

1.17

Activations Density 0.530%

regular expressions and code snippets related to parsing or manipulating text

No Comments

No Known Activations