INDEX

Explanations

mentions of technical documentation, guides, or job descriptions

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>

-3.30

/**

-1.13

<?

-1.00

ⓧ

-0.97

/*

-0.91

DockStyle

-0.84

<?

-0.81

/*++

-0.76

-0.75

disposing

-0.73

POSITIVE LOGITS

 maneu

1.53

 affor

1.50

 increa

1.44

 Minang

1.43

 impra

1.43

 reluct

1.41

Juf

1.41

 disreg

1.40

 accla

1.40

 disagre

1.37

Activations Density 1.051%

mentions of technical documentation, guides, or job descriptions

No Comments

No Known Activations