INDEX

Explanations

terms related to network technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tartalomajánló

-0.84

abestanden

-0.81

 defaultstate

-0.81

 ویکی‌پدیای

-0.77

casian

-0.71

IUrlHelper

-0.71

StoryboardSegue

-0.71

ziasztok

-0.71

Viited

-0.68

CppMethod

-0.68

POSITIVE LOGITS

Net

1.62

net

1.38

Net

1.25

NET

1.22

 Nets

1.13

 nets

0.99

NET

0.93

net

0.92

Nets

0.87

 netted

0.84

Activations Density 0.224%

terms related to network technologies

No Comments

No Known Activations