INDEX

Explanations

statistical terms and measures related to data analysis

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

SequentialGroup

-0.67

uría

-0.55

thunk

-0.54

vins

-0.54

ষ্

-0.54

Enllaces

-0.52

RTEE

-0.52

 IFTT

-0.51

RunAsync

-0.51

Хьажоргаш

-0.50

POSITIVE LOGITS

 again

0.81

again

0.70

 Again

0.66

Again

0.63

 AGAIN

0.57

исленность

0.52

 novamente

0.51

routeProvider

0.48

bootstrapcdn

0.48

RectangleBorder

0.46

Activations Density 0.877%

statistical terms and measures related to data analysis

No Comments

No Known Activations