INDEX

Explanations

legal terms and documents, including disclaimers, disallowed actions, and discrimination cases

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>

-2.80

ⓧ

-0.82

/**

-0.73

Autoritní

-0.72

stereotype

-0.67

 Rome

-0.65

smarty

-0.65

AndroidJUnit

-0.64

omock

-0.63

UTF

-0.62

POSITIVE LOGITS

 dises

1.83

 stockholm

1.58

fta

1.54

 frankfurt

1.54

 budapest

1.54

ftu

1.54

 riviera

1.51

 ibiza

1.51

 squa

1.50

 bandung

1.48

Activations Density 0.191%

legal terms and documents, including disclaimers, disallowed actions, and discrimination cases

No Comments

No Known Activations