INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-2.13

ⓧ

-1.17

/**

-1.03

<?

-0.96

-0.95

/*

-0.93

 springfox

-0.79

public

-0.74

<?

-0.73

 continue

-0.73

POSITIVE LOGITS

 affor

2.08

 maneu

1.99

Juf

1.96

 increa

1.94

 stockholm

1.94

 impra

1.91

 lidl

1.91

 accla

1.87

 véhic

1.86

 Intere

1.84

Activations Density 0.196%

No Comments

No Known Activations