INDEX

Explanations

terms related to technical concepts and programming languages, particularly focusing on interfaces, attribution theory, hyphea, and column partitioning

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 persil

-0.83

 franz

-0.81

 trico

-0.81

 fluo

-0.75

 Schrö

-0.74

 Keny

-0.73

 tinte

-0.73

 thermomix

-0.73

 bayern

-0.72

Nö

-0.71

POSITIVE LOGITS

 also

1.03

also

0.84

can

0.75

 ayrıca

0.75

 consists

0.72

 includes

0.72

 inoltre

0.71

 cannot

0.70

 differs

0.70

 represents

0.70

Activations Density 0.290%

terms related to technical concepts and programming languages, particularly focusing on interfaces, attribution theory, hyphea, and column partitioning

No Comments

No Known Activations