INDEX

Explanations

references to specific entities and organizations, particularly related to government and infrastructure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

RectangleBorder

-0.61

DebuggerNonUser

-0.57

 Orrell

-0.54

 Genu

-0.50

 epile

-0.50

>");

-0.48

endphp

-0.48

bró

-0.47

Gover

-0.47

 bezeichneter

-0.47

POSITIVE LOGITS

:✨

0.96

cr

0.95

 crush

0.95

 crushing

0.90

 crushed

0.89

Param

0.84

 crushes

0.83

 swept

0.80

+:+

0.77

crush

0.76

Activations Density 0.117%

references to specific entities and organizations, particularly related to government and infrastructure

No Comments

No Known Activations