INDEX

Explanations

phrases related to conflicts and dispute resolution

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>

-3.33

-0.93

<?

-0.83

/**

-0.70

ⓧ

-0.68

/*!

-0.66

#![

-0.61

/***

-0.60

add

-0.58

<?

-0.58

POSITIVE LOGITS

 stockholm

1.48

 bandung

1.36

 affor

1.35

kyo

1.35

 jaya

1.30

aen

1.28

 wien

1.26

 Minang

1.24

 conflic

1.23

 haup

1.23

Activations Density 0.068%

phrases related to conflicts and dispute resolution

No Comments

No Known Activations