INDEX

Explanations

proper nouns with multiple parts and numbers

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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

-0.85

ⓧ

-0.78

<?

-0.76

 Shakspeare

-0.70

 thut

-0.66

 adjour

-0.62

/**

-0.60

 unlaw

-0.58

Litteratur

-0.57

 tranf

-0.56

POSITIVE LOGITS

ef

2.04

eb

1.89

ef

1.14

eff

1.12

EF

1.11

eff

1.09

Eff

1.03

Eff

1.00

EB

0.97

Ef

0.94

Activations Density 0.242%

proper nouns with multiple parts and numbers

No Comments

No Known Activations

proper nouns with multiple parts and numbers

No Comments

No Known Activations