INDEX

Explanations

personal pronouns used in conjunction with actions or experiences

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-2.60

ⓧ

-0.94

/*

-0.78

/**

-0.78

<?

-0.77

-0.76

/***

-0.76

public

-0.75

<?

-0.74

-0.72

POSITIVE LOGITS

 affor

2.20

 maneu

2.18

 impra

2.15

 disagre

2.13

 accla

2.13

 reluct

2.05

 increa

1.99

 shenan

1.97

 stockholm

1.93

 apprehen

1.93

Activations Density 0.367%

personal pronouns used in conjunction with actions or experiences

No Comments

No Known Activations