INDEX

Explanations

rules and regulations related to a particular space or activity

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>

-2.93

/*

-0.93

 […]

-0.91

/**

-0.84

-0.73

ⓧ

-0.73

<?

-0.73

 mobilize

-0.68

/*!

-0.66

 阅读

-0.66

POSITIVE LOGITS

 mikrofon

1.33

 silikon

1.23

 alkoh

1.18

 keramik

1.16

 optik

1.14

 seksi

1.13

 demokra

1.11

 antik

1.07

 praktik

1.07

 kosme

1.05

Activations Density 1.650%

rules and regulations related to a particular space or activity

No Comments

No Known Activations