INDEX

Explanations

descriptive information about physical locations or spaces

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>

-3.28

/***

-0.86

<?

-0.81

/**

-0.80

ⓧ

-0.73

/*

-0.66

/*!

-0.65

 encourage

-0.64

#![

-0.64

 respond

-0.64

POSITIVE LOGITS

Juf

1.45

 lele

1.43

 Keny

1.39

 Ferdin

1.32

 dises

1.27

 bordeaux

1.26

 casio

1.25

mef

1.24

 roul

1.24

 ankara

1.24

Activations Density 0.094%

descriptive information about physical locations or spaces

No Comments

No Known Activations