INDEX

Explanations

programming-related keywords and methods in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

出版年

-0.60

期刊论文

-0.59

/**

-0.54

quium

-0.53

MENAFN

-0.52

Referències

-0.52

例句

-0.52

 dinámico

-0.51

reactstrap

-0.51

 NSCoder

-0.51

POSITIVE LOGITS

setContentView

0.69

ExecutionContext

0.61

parsedMessage

0.59

WSGI

0.56

cloudflare

0.55

glDelete

0.55

putExtra

0.55

principalColumn

0.54

ard

0.54

 findViewById

0.54

Activations Density 1.826%

programming-related keywords and methods in code snippets

No Comments

No Known Activations