INDEX

Explanations

terms and identifiers related to programming concepts and object references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 autorytatywna

-1.02

 arşivlendi

-0.66

enumii

-0.65

 ब्रेकडाउन

-0.63

 disambiguazione

-0.62

ChildScrollView

-0.60

 purpoſe

-0.59

 detailsLots

-0.59

execSQL

-0.59

 مشين

-0.58

POSITIVE LOGITS

and

0.43

 name

0.40

UniformLocation

0.39

name

0.37

principalColumn

0.35

 uuidv

0.35

 NAME

0.35

 identifier

0.34

onedDateTime

0.34

 cheiro

0.32

Activations Density 0.582%

terms and identifiers related to programming concepts and object references

No Comments

No Known Activations