INDEX

Explanations

references to measurements or quantities, especially expressed in metric terms like millimeters or milliliters

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

 earnestness

-0.77

rehensive

-0.73

<bos>

-0.73

 impelled

-0.71

 endeavored

-0.70

Mmmm

-0.70

 ardor

-0.68

Bullshit

-0.68

Hahahahaha

-0.67

Derp

-0.66

POSITIVE LOGITS

 klassi

0.92

 kompati

0.89

 katastro

0.84

 rafraî

0.83

 flé

0.82

iI

0.80

 Bakter

0.79

 kritis

0.79

 Schrö

0.77

 autenti

0.77

Activations Density 1.020%

references to measurements or quantities, especially expressed in metric terms like millimeters or milliliters

No Comments

No Known Activations