INDEX

Explanations

information related to official names and designations

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>

-2.20

-0.86

/**

-0.85

<?

-0.84

ⓧ

-0.78

<?

-0.66

/*

-0.64

 apply

-0.56

нился

-0.53

jsdelivr

-0.52

POSITIVE LOGITS

 napoli

1.04

 santiago

1.01

 sovere

0.96

 ricardo

0.91

 sergio

0.89

 fernando

0.89

 eduardo

0.88

 valencia

0.88

 toledo

0.88

 bandung

0.88

Activations Density 0.859%

information related to official names and designations

No Comments

No Known Activations