INDEX

Explanations

mentions of eating or dining 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>

-1.30

public

-0.76

get

-0.75

export

-0.74

ുറ

-0.73

-0.71

/**

-0.70

be

-0.70

CreateIndex

-0.70

 offer

-0.69

POSITIVE LOGITS

 affor

2.51

 maneu

2.50

 accla

2.31

 impra

2.30

 increa

2.29

 stockholm

2.21

 emphat

2.17

 reluct

2.14

 lidl

2.13

 excru

2.11

Activations Density 0.106%

mentions of eating or dining experiences

No Comments

No Known Activations