INDEX

Explanations

references to literary works or discussions about literature

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

DMETHOD

-0.70

TestingModule

-0.63

 XCTest

-0.62

routeProvider

-0.59

 HasFactory

-0.59

原始内容存档于

-0.59

UserScript

-0.58

 numberOfRows

-0.58

batore

-0.57

issements

-0.56

POSITIVE LOGITS

LIT

0.57

期刊论文

0.57

ERAL

0.57

Lit

0.56

0.55

Lit

0.53

mus

0.53

tles

0.53

lit

0.52

ⓧ

0.52

Activations Density 0.094%

references to literary works or discussions about literature

No Comments

No Known Activations