INDEX

Explanations

references to websites or website-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 InputDecoration

-0.76

 numerus

-0.75

°•

-0.72

clinical

-0.72

 scratch

-0.67

PREFERRED

-0.67

SneakyThrows

-0.67

 CountDown

-0.67

 Gentry

-0.64

 ?>">

-0.64

POSITIVE LOGITS

 Website

1.59

 website

1.58

 websites

1.54

website

1.51

 WEBSITE

1.44

Website

1.44

 Websites

1.41

WEBSITE

1.37

websites

1.30

Websites

1.26

Activations Density 0.031%

references to websites or website-related content

No Comments

No Known Activations