INDEX

Explanations

technical terms and structures related to programming, specifically around functions and data handling 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

getOutputStream

-0.43

 برف

-0.42

pí

-0.41

qu

-0.41

synthesize

-0.41

BindView

-0.40

“

-0.40

 darauf

-0.40

pis

-0.39

QMessageBox

-0.39

POSITIVE LOGITS

 nahilalakip

0.74

CloseOperation

0.73

 transfieras

0.73

 autorytatywna

0.69

 protoimpl

0.68

 насељу

0.67

íncia

0.67

principalColumn

0.66

migrationBuilder

0.66

хьтан

0.65

Activations Density 0.121%

technical terms and structures related to programming, specifically around functions and data handling in code

No Comments

No Known Activations