INDEX

Explanations

names of places

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>

-3.35

ⓧ

-1.01

<?

-0.98

/***

-0.93

/**

-0.79

-0.70

/*

-0.70

#![

-0.64

/*!

-0.62

/*++

-0.61

POSITIVE LOGITS

 wien

1.36

 magis

1.32

 bayern

1.30

 lele

1.30

 milano

1.26

 fatis

1.23

 stockholm

1.22

 bandung

1.21

 eiffel

1.21

 unlaw

1.20

Activations Density 0.228%

names of places

No Comments

No Known Activations