INDEX

Explanations

mentions of losing or being lost

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.27

Kontrola

-0.71

 inform

-0.68

public

-0.65

quad

-0.64

</thead>

-0.63

Autoritní

-0.63

///**

-0.63

</tbody>

-0.63

//};

-0.62

POSITIVE LOGITS

 maneu

1.73

 emphat

1.66

 wien

1.64

 stockholm

1.62

Juf

1.62

 dises

1.56

ftu

1.55

 increa

1.55

 Minang

1.54

 bandung

1.53

Activations Density 0.164%

mentions of losing or being lost

No Comments

No Known Activations