INDEX

Explanations

references to tools and infrastructure in technical contexts

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

"tool" or similar

np_acts-logits-general · gemini-2.0-flash

tools and tips

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

GEBURTSDATUM

-0.63

ChildScrollView

-0.59

ly

-0.59

abestanden

-0.58

IBOutlet

-0.54

 CommandType

-0.53

BagConstraints

-0.51

EndGlobalSection

-0.50

hoeddwyd

-0.50

 TMPro

-0.49

POSITIVE LOGITS

kits

1.21

kit

1.09

Kit

0.92

 kits

0.91

Kit

0.91

KIT

0.86

kit

0.82

boxes

0.78

tips

0.74

KIT

0.71

Activations Density 0.115%

references to tools and infrastructure in technical contexts

"tool" or similar

tools and tips

No Comments

No Known Activations