INDEX

Explanations

identifiers and terms related to governmental and scientific projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ništ

-0.46

poel

-0.40

erráneo

-0.38

 Never

-0.38

oo

-0.38

 τους

-0.36

Never

-0.36

 Réalisation

-0.35

ViewGroup

-0.35

 relevant

-0.35

POSITIVE LOGITS

 AssemblyCulture

1.15

tvguidetime

0.84

出版年

0.81

lapsingToolbar

0.81

complexContent

0.76

তথ্যসূত্র

0.71

Kjelder

0.70

IUrlHelper

0.68

EXTERN

0.68

 vété

0.66

Activations Density 0.844%

identifiers and terms related to governmental and scientific projects

No Comments

No Known Activations