INDEX

Explanations

promotional messages or calls to action typically related to news or articles

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>

-3.05

ⓧ

-1.10

-1.07

<?

-0.94

/***

-0.87

/**

-0.85

<?

-0.84

#![

-0.78

/*

-0.76

↘

-0.71

POSITIVE LOGITS

 lele

1.73

 wien

1.61

 maroc

1.59

 marseille

1.54

 milano

1.53

 bayern

1.52

 napoli

1.52

 riviera

1.50

 bandung

1.49

 dises

1.49

Activations Density 0.101%

promotional messages or calls to action typically related to news or articles

No Comments

No Known Activations