INDEX

Explanations

elements and syntax specific to programming languages, particularly related to function definitions and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

mapreduce

-0.50

yntaxException

-0.49

 eventdata

-0.46

argout

-0.44

 кан

-0.43

ResourceManager

-0.43

belline

-0.41

tigma

-0.40

robi

-0.40

lwjgl

-0.40

POSITIVE LOGITS

expandindo

0.72

SuppressLint

0.68

 lenker

0.64

stdint

0.62

$[-

0.61

RequestQueue

0.61

🥲

0.60

ancias

0.60

 licence

0.59

[...,

0.59

Activations Density 0.313%

elements and syntax specific to programming languages, particularly related to function definitions and data types

No Comments

No Known Activations