INDEX

Explanations

the word "detection" or "detected" in various contexts including in academic papers, disease detection, and quarantine measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.19

public

-0.75

//

-0.72

-0.71

-0.70

/*

-0.69

/**

-0.69

↵↵

-0.66

add

-0.65

POSITIVE LOGITS

 affor

2.07

 increa

2.01

 maneu

1.96

fta

1.94

 détect

1.92

 detection

1.90

 Detection

1.90

Juf

1.90

ftu

1.89

 thut

1.89

Activations Density 0.097%

the word "detection" or "detected" in various contexts including in academic papers, disease detection, and quarantine measures

No Comments

No Known Activations