INDEX

Explanations

elements of code related to functions and error handling

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

Tokens followed by the word "function"

np_acts-logits-general · gemini-2.0-flash

javascript function definitions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

SPATH

-0.67

 كومونز

-0.55

SocketChannel

-0.54

principalTable

-0.54

 оригіналу

-0.51

BASEPATH

-0.51

tahui

-0.50

RenderAtEndOf

-0.48

TestBed

-0.48

خصة

-0.47

POSITIVE LOGITS

 function

2.11

function

2.02

 fonction

1.09

 función

1.08

 Function

1.07

 Funktion

1.04

 FUNCTION

1.01

 functioned

1.00

 funzione

0.99

 функ

0.98

Activations Density 0.113%

elements of code related to functions and error handling

Tokens followed by the word "function"

javascript function definitions

No Comments

No Known Activations