INDEX

Explanations

function annotations and documentation tags in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

to

-0.50

-0.44

in

-0.44

Car

-0.43

 palmas

-0.42

↵↵

-0.41

 with

-0.41

 Double

-0.40

POSITIVE LOGITS

 الحره

1.31

 Signalez

1.22

styleType

1.10

évaluateur

1.09

 autorytatywna

1.09



1.06

 myſelf

1.06

fjspx

1.04

 itſelf

1.03

TagMode

1.03

Activations Density 0.082%

function annotations and documentation tags in code

No Comments

No Known Activations