INDEX

Explanations

statements related to giving or contributing, such as donations and gifts

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>

-3.57

ⓧ

-1.13

<?

-1.07

/**

-0.99

-0.90

/*++

-0.84

/***

-0.82

/*!

-0.77

<?

-0.77

/*

-0.75

POSITIVE LOGITS

Juf

1.21

 véhic

1.20

 bandung

1.18

 considér

1.18

 quoique

1.16

 tramont

1.13

 Minang

1.13

 sappi

1.12

 ibiza

1.10

 pleins

1.10

Activations Density 0.937%

statements related to giving or contributing, such as donations and gifts

No Comments

No Known Activations