INDEX

Explanations

terms related to furniture

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.47

ⓧ

-0.90

-0.85

/**

-0.78

 interposed

-0.74

 intersper

-0.71

 encomp

-0.71

<?

-0.70

 reconno

-0.69

 defray

-0.69

POSITIVE LOGITS

 furniture

1.38

 Furniture

1.25

furniture

1.13

Furniture

1.10

 FURNITURE

1.01

 furnishings

0.93

 Möbel

0.80

 muebles

0.80

caucasian

0.78

 furn

0.76

Activations Density 0.202%

terms related to furniture

No Comments

No Known Activations