INDEX

Explanations

references to territorial behavior or ownership

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>

-2.20

-0.69

<?

-0.62

 initComponents

-0.58

 clinch

-0.57

 inject

-0.57

Jîn

-0.55

/**

-0.55

πάρχ

-0.55

/*

-0.54

POSITIVE LOGITS

 territory

1.39

territory

1.33

Territory

1.30

 oleo

1.24

 bordeaux

1.23

 parma

1.17

 swarovski

1.15

 cabrio

1.14

 levis

1.13

 Territory

1.13

Activations Density 0.222%

references to territorial behavior or ownership

No Comments

No Known Activations