INDEX

Explanations

information related to policies, procedures, and terms and conditions in documents, as well as references to specific individuals and events

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>

-2.69

ⓧ

-1.12

-0.87

/**

-0.87

/*++

-0.85

<?

-0.82

/*

-0.80

<?

-0.74

RRect

-0.62

DockStyle

-0.62

POSITIVE LOGITS

 maneu

1.41

 Minang

1.38

 reluct

1.35

 affor

1.33

 Keny

1.33

 accla

1.31

 disagre

1.25

 lele

1.23

Juf

1.21

 intermitt

1.20

Activations Density 0.929%

information related to policies, procedures, and terms and conditions in documents, as well as references to specific individuals and events

No Comments

No Known Activations