INDEX

Explanations

negative or critical language

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

/**

-0.92

-0.90

ⓧ

-0.88

/***

-0.88

<?

-0.70

/*

-0.68

 intersper

-0.66

///**

-0.64

/*!

-0.63

POSITIVE LOGITS

 signora

1.16

 cioc

1.12

 bandung

1.11

 maroc

1.08

 lele

1.07

 toscana

1.06

 ananas

1.06

 jawa

1.06

 cammin

1.04

 divertimento

1.03

Activations Density 0.186%

negative or critical language

No Comments

No Known Activations