INDEX

Explanations

occurrences of the phrase "new" and related patterns 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 @ 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

…).

-0.52

…)

-0.52

usitis

-0.51

kia

-0.50

itores

-0.49

...)

-0.49

etcode

-0.48

verwijspagina

-0.48

ⓘ

-0.47

///<

-0.47

POSITIVE LOGITS

openqa

0.75

$_"

0.75

 ProtoMessage

0.74

 Bewußt

0.69

 Monfieur

0.68

Hentet

0.68

(\<

0.66

culously

0.66

 Jefus

0.66

$_(

0.66

Activations Density 0.043%

occurrences of the phrase "new" and related patterns in programming contexts

No Comments

No Known Activations