INDEX

Explanations

references to forest-related topics

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>

-3.00

-0.77

/**

-0.75

ⓧ

-0.73

 mobilize

-0.70

<?

-0.69

/***

-0.66

<?

-0.65

 relocate

-0.64

/*

-0.63

POSITIVE LOGITS

 Minang

1.32

 bandung

1.30

 Jambi

1.23

 jati

1.22

 lele

1.21

Juf

1.20

 jaya

1.20

 silva

1.16

 Forest

1.15

 Palembang

1.13

Activations Density 0.075%

references to forest-related topics

No Comments

No Known Activations