INDEX

Explanations

specific amusement park attractions related to a famous movie series

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

•Interesting activations

Very clearly activates on terms related to the Harry Potter franchise, but also contains some amount of knowledge of Star Wars

No Comments

Negative Logits

<bos>

-2.63

ⓧ

-0.96

/**

-0.75

-0.74

<?

-0.74

SequentialGroup

-0.74

 initComponents

-0.74

HasIndex

-0.73

зулта

-0.72

 jsPsych

-0.71

POSITIVE LOGITS

 affor

2.02

 maneu

1.96

 increa

1.88

 volunte

1.83

 fortn

1.81

 wien

1.81

 impra

1.79

fta

1.78

 stockholm

1.77

 strick

1.77

Activations Density 0.209%

specific amusement park attractions related to a famous movie series

No Comments

No Known Activations