INDEX

Explanations

references to domestic spaces and personal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 صوتيه

-0.45

dbl

-0.44

vierno

-0.40

ison

-0.40

handleSubmit

-0.40

hadur

-0.39

holt

-0.38

dataTables

-0.38

isca

-0.37

 ujednoznacz

-0.37

POSITIVE LOGITS

MessageTagHelper

0.77

 StatelessWidget

0.74

 residence

0.74

 initComponents

0.73

 pessoais

0.72

#+#

0.72

 roommate

0.72

Demografie

0.72

 roommates

0.71

 AssemblyCompany

0.70

Activations Density 0.491%

references to domestic spaces and personal relationships

No Comments

No Known Activations