INDEX

Explanations

references to procedures and techniques

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>

-3.39

<?

-0.89

ⓧ

-0.86

/**

-0.82

/***

-0.76

 nahilalakip

-0.69

 kasarigan

-0.68

<?

-0.68

Jeografia

-0.67

POSITIVE LOGITS

 affor

1.44

 maneu

1.35

 accla

1.20

 increa

1.20

 disagre

1.19

 reluct

1.18

 volunte

1.17

 véhic

1.15

 shenan

1.13

 impra

1.12

Activations Density 0.522%

references to procedures and techniques

No Comments

No Known Activations