INDEX

Explanations

mentions or titles related to academic degrees, programs, and educational resources

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>

-3.23

//---

-0.74

/***

-0.70

HasIndex

-0.68

/*++

-0.67

//{

-0.67

<?

-0.66

public

-0.63

url

-0.61

//--

-0.59

POSITIVE LOGITS

 affor

1.45

 increa

1.43

 stockholm

1.42

Juf

1.41

 Minang

1.39

 véhic

1.37

 Keny

1.35

 sovere

1.32

 accla

1.31

 excru

1.27

Activations Density 0.083%

mentions or titles related to academic degrees, programs, and educational resources

No Comments

No Known Activations