INDEX

Explanations

terms related to file or access permissions in a computer context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 sustainability

-0.49

études

-0.46

 Buying

-0.45

QUOTE

-0.44

 Gué

-0.43

 Cade

-0.43

 quote

-0.43

enosti

-0.42

 QUOTE

-0.42

 Brand

-0.42

POSITIVE LOGITS

 Windows

0.88

 ActiveX

0.72

 Firefox

0.71

 Linux

0.69

 Microsoft

0.68

 OneDrive

0.67

 Adobe

0.66

 macOS

0.66

 Android

0.66

 iCloud

0.65

Activations Density 0.168%

terms related to file or access permissions in a computer context

No Comments

No Known Activations