INDEX

Explanations

boolean values in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Exacts

-0.91

IntoConstraints

-0.91

 חיצוניים

-0.85

 nakalista

-0.85

קישורים

-0.84

EDEFAULT

-0.83

出版年

-0.80

MENAFN

-0.79

󠁿

-0.79

 Exactos

-0.78

POSITIVE LOGITS

 toros

0.45

 presidencial

0.41

 stond

0.40

 مرئيه

0.37

OneToOne

0.37

 Crot

0.36

 spolup

0.36

 службу

0.35

larının

0.35

ператор

0.35

Activations Density 0.092%

boolean values in programming contexts

No Comments

No Known Activations