INDEX

Explanations

phrases related to authorship and acknowledgment of contributions in research

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

-0.49

DNA

-0.47

 blood

-0.46

getOne

-0.44

One

-0.43

 courts

-0.42

 πυ

-0.42

вольно

-0.41

 getStart

-0.41

POSITIVE LOGITS

 ویکی‌پدی

0.98

 NSCoder

0.96

QMetaType

0.91

%>%

0.82

 Савезне

0.82

GEBURTSDATUM

0.82

 mergeFrom

0.81

numerusform

0.80

protoc

0.78

ThroughAttribute

0.76

Activations Density 0.822%

phrases related to authorship and acknowledgment of contributions in research

No Comments

No Known Activations