INDEX

Explanations

details related to a crime or incident, such as the use of chemicals, injuries sustained, medical treatment, charges filed, and appeals for information

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>

-1.89

anță

-0.83

ിൽ

-0.83

 realize

-0.78

ാൻ

-0.76

 favor

-0.75

িয়ে

-0.75

ൾ

-0.75

 labor

-0.75

ⓧ

-0.74

POSITIVE LOGITS

 Mejía

1.43

 indestru

1.39

 Darío

1.38

 maneu

1.37

ftu

1.35

 véhic

1.32

hcm

1.29

 thut

1.28

 Cáceres

1.27

 embodi

1.27

Activations Density 1.978%

details related to a crime or incident, such as the use of chemicals, injuries sustained, medical treatment, charges filed, and appeals for information

No Comments

No Known Activations