INDEX

Explanations

mentions of numerical or alphanumeric patterns

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>

-2.63

 inaugurate

-0.57

 activate

-0.56

ⓧ

-0.54

 rehabilitate

-0.53

 promote

-0.52

 mobilize

-0.51

عرض

-0.50

يع

-0.49

 assist

-0.49

POSITIVE LOGITS

1.02

 Minang

0.90

 malheure

0.87

 kristal

0.86

;;)

0.86

 tehd

0.85

 désol

0.84

 Manufact

0.83

 pleins

0.81

Activations Density 0.089%

mentions of numerical or alphanumeric patterns

No Comments

No Known Activations