INDEX

Explanations

terms related to intelligence and national security

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>

-2.00

 intersper

-1.55

 encomp

-1.50

 vainly

-1.36

 unspeak

-1.31

 gratify

-1.25

 shenan

-1.19

 reconno

-1.17

 impelled

-1.16

 rouse

-1.14

POSITIVE LOGITS

 intelligence

1.39

 Intelligence

1.35

Intel

1.33

 Intel

1.27

intelligence

1.22

Intelligence

1.20

intel

1.07

 intel

1.04

 INTELL

0.98

 intelig

0.95

Activations Density 0.182%

terms related to intelligence and national security

No Comments

No Known Activations