INDEX

Explanations

detectives and references to scanning in various contexts

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

 AssemblyCulture

-0.81

 Pyle

-0.72

CardContent

-0.69

accordo

-0.67

git

-0.67

++++++++++++++++

-0.66

 microondas

-0.62

Доброго

-0.62

 שכ

-0.62

getShared

-0.61

POSITIVE LOGITS

 SCAN

1.45

 scan

1.44

SCAN

1.36

 Scan

1.35

 scans

1.30

 scanning

1.30

Scan

1.27

scan

1.24

 scanner

1.21

 Scanning

1.17

Activations Density 0.144%

detectives and references to scanning in various contexts

No Comments

No Known Activations