INDEX

Explanations

proper nouns related to politics, economics, and personal names

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>

-3.53

-1.00

ⓧ

-0.98

/**

-0.81

<?

-0.80

Kontrola

-0.79

 shuddered

-0.73

 shivered

-0.69

 banish

-0.67

 springfox

-0.66

POSITIVE LOGITS

 quoique

1.42

 catég

1.40

 éto

1.40

 véhic

1.38

 soulign

1.37

 rafra

1.37

 délib

1.37

 énon

1.29

 pleins

1.26

 habile

1.26

Activations Density 0.569%

proper nouns related to politics, economics, and personal names

No Comments

No Known Activations