INDEX

Explanations

informational sources or references mentioned in content

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>

-3.47

ⓧ

-0.94

/**

-0.71

/*

-0.70

<?

-0.69

-0.67

<?

-0.67

/***

-0.67

 springfox

-0.65

//---

-0.62

POSITIVE LOGITS

 lele

1.45

 affor

1.36

 accla

1.25

 thuy

1.24

Juf

1.21

 swarovski

1.19

 quoc

1.19

 nuoc

1.18

 unlaw

1.18

 impra

1.16

Activations Density 0.090%

informational sources or references mentioned in content

No Comments

No Known Activations