INDEX

Explanations

phrases related to information security and tech processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.59

<?

-0.92

ⓧ

-0.85

/***

-0.81

posób

-0.81

Transcripción

-0.78

/**

-0.76

/*++

-0.72

/*!

-0.70

POSITIVE LOGITS

 Momb

0.97

 délib

0.95

 véhic

0.92

 lele

0.92

 épu

0.89

 Potenti

0.89

 catég

0.89

 Somal

0.87

 Propag

0.85

 pleins

0.84

Activations Density 1.339%

phrases related to information security and tech processes

No Comments

No Known Activations