INDEX

Explanations

function definitions and their associated operations

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

Programming-related actions

np_acts-logits-general · gemini-2.0-flash

computational actions

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

gonic

-0.62

 Audiodateien

-0.61

VersionUID

-0.61

客様

-0.55

 CGRectMake

-0.55

 torchvision

-0.54

crollView

-0.50

 jadx

-0.50

 bodyParser

-0.48

 QtCore

-0.47

POSITIVE LOGITS

AndSet

0.79

 existing

0.74

 them

0.71

 Theſe

0.70

new

0.70

 pauv

0.69

able

0.69

 lại

0.68

all

0.66

一下

0.65

Activations Density 0.323%

function definitions and their associated operations

Programming-related actions

computational actions

No Comments

No Known Activations