INDEX

Explanations

references to programming and technical problems related to system behavior and debugging

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

something "working" or "not working."

np_acts-logits-general · gemini-2.0-flash

working or not working

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

 CreateTagHelper

-0.78

rungsseite

-0.72

UrlResolution

-0.67

sidemargin

-0.61

 consultato

-0.56

DoubleQuotes

-0.56

ViewImports

-0.54

 ComVisible

-0.54

nommen

-0.53

polated

-0.52

POSITIVE LOGITS

 working

3.10

working

2.66

 worked

2.57

 work

2.56

 Working

2.47

Working

2.46

 works

2.36

 WORKING

2.35

WORKING

2.28

worked

2.16

Activations Density 0.609%

references to programming and technical problems related to system behavior and debugging

something "working" or "not working."

working or not working

No Comments

No Known Activations