INDEX

Explanations

technical terms and elements related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

or

-0.50

am

-0.49

 should

-0.48

]--;

-0.47

but

-0.44

 rest

-0.43

pé

-0.43

int

-0.42

 best

-0.42

qu

-0.42

POSITIVE LOGITS

 يتيمه

0.88

 فريبيس

0.79

 xenia

0.76

 للمعارف

0.76

 الحره

0.75

RenderAtEndOf

0.75

 trident

0.74

 ulcers

0.74

adaptiveStyles

0.72

 mortars

0.71

Activations Density 0.232%

technical terms and elements related to programming and software development

No Comments

No Known Activations