INDEX

Explanations

references to specific programming classes and methods, particularly relating to data operations and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HomeAsUpEnabled

-0.63

fion

-0.62

 CGRectMake

-0.61

 Albanian

-0.60

 '../../

-0.59

randomUUID

-0.59

 Analy

-0.59

 Confucian

-0.59

 CGRect

-0.58

ynomial

-0.58

POSITIVE LOGITS

NS

2.30

NS

2.29

ns

1.54

ns

1.40

Ns

1.09

NSM

1.00

Ns

0.94

 AspNetCore

0.91

НС

0.83

AutoresizingMask

0.83

Activations Density 0.043%

references to specific programming classes and methods, particularly relating to data operations and types

No Comments

No Known Activations