INDEX

Explanations

programming-related terminology and functions

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

File names for figures/plots

np_acts-logits-general · gemini-2.0-flash

figure references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

GenerationType

-0.53

 disambiguazione

-0.53

Portály

-0.52

 SqlCommand

-0.50

Personensuche

-0.49

ByExample

-0.49

 okuyayım

-0.48

FileInputStream

-0.48

stateProvider

-0.48

HtmlAttribute

-0.48

POSITIVE LOGITS

fig

0.94

 figure

0.92

figure

0.90

fig

0.83

 figures

0.76

 Figura

0.73

igure

0.71

 figs

0.71

 figura

0.71

figs

0.70

Activations Density 0.644%

programming-related terminology and functions

File names for figures/plots

figure references

No Comments

No Known Activations