INDEX

Explanations

programming-related keywords, particularly those related to annotations and buffer management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

+#+#

-0.54

 onBind

-0.53

styleable

-0.52

 CURIAM

-0.52

 linkovi

-0.49

ipt

-0.49

structure

-0.48

CAPE

-0.48

canestro

-0.48

ungi

-0.48

POSITIVE LOGITS

addPreferredGap

0.85

includegraphics

0.66

 magasiner

0.64

/');

0.63

yce

0.62

 FetchType

0.61

 jsPsych

0.61

']);

0.60

ściu

0.60

帖最后由

0.60

Activations Density 1.729%

programming-related keywords, particularly those related to annotations and buffer management

No Comments

No Known Activations