INDEX

Explanations

terms and phrases related to models and data structures in programming

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

//});

-0.45

int

-0.41

param

-0.41

The

-0.40

 karta

-0.40

 outside

-0.40

old

-0.39

 tastes

-0.39

now

-0.39

We

-0.39

POSITIVE LOGITS

WebElementEntity

0.93

aarrggbb

0.86

 Réponses

0.83

 propOrder

0.81

thâu

0.79

uxxxx

0.78

etcode

0.78

 nakalista

0.74

 Waray

0.74

Демографія

0.71

Activations Density 0.151%

terms and phrases related to models and data structures in programming

No Comments

No Known Activations