INDEX

Explanations

mentions of specific names and organizations

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>

-3.00

-1.10

ⓧ

-0.95

/*++

-0.94

/**

-0.94

<?

-0.92

/*!

-0.85

<?

-0.82

#![

-0.72

/*

-0.70

POSITIVE LOGITS

Juf

1.96

 thut

1.87

aen

1.75

 effe

1.73

 Intere

1.72

 unlaw

1.71

 sovere

1.70

 increa

1.70

 inev

1.69

 maneu

1.69

Activations Density 0.471%

mentions of specific names and organizations

No Comments

No Known Activations