INDEX

Explanations

terms related to programming languages and their components

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

SourceChecksum

-0.46

köz

-0.44

 numerus

-0.44

idän

-0.43

jeta

-0.43

meti

-0.42

 Minor

-0.41

<?,

-0.41

stru

-0.41

ží

-0.40

POSITIVE LOGITS

出版年

0.81

MENAFN

0.80

 فريبيس

0.79

 referenties

0.74

RenderAtEndOf

0.74

parsedMessage

0.73

 TextInputType

0.72

PyExc

0.72

 مشين

0.70

 Whence

0.68

Activations Density 1.052%

terms related to programming languages and their components

No Comments

No Known Activations