INDEX

Explanations

function definitions and related annotations in programming 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

 käytet

-0.45

зме

-0.44

 StringBuffer

-0.43

 joan

-0.42

 jotka

-0.42

 tider

-0.40

 zabud

-0.40

Under

-0.40

 ragioni

-0.40

 لقد

-0.39

POSITIVE LOGITS

 EconPapers

0.92

 kasarigan

0.81

 typelib

0.78

MemoryWarning

0.77

principalTable

0.70

 незавершена

0.67

 BoxFit

0.67

IntoConstraints

0.65

 uLocal

0.65

matician

0.63

Activations Density 0.155%

function definitions and related annotations in programming code

No Comments

No Known Activations