INDEX

Explanations

text related to policy changes or modifications in guidelines

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-1.88

ⓧ

-1.16

-1.02

/**

-1.01

/*

-0.98

<?

-0.95

/*++

-0.85

#![

-0.81

<?

-0.80

-0.78

POSITIVE LOGITS

 affor

1.61

 wien

1.60

 jaya

1.57

 bandung

1.57

 increa

1.53

hcm

1.51

 maneu

1.51

 maroc

1.50

 lele

1.49

aen

1.48

Activations Density 0.107%

text related to policy changes or modifications in guidelines

No Comments

No Known Activations