INDEX

Explanations

specific criteria listed in documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.03

/***

-0.83

ⓧ

-0.78

-0.71

<?

-0.69

/**

-0.61

/*!

-0.59

 reclaim

-0.59

/*++

-0.59

 modernize

-0.57

POSITIVE LOGITS

 criteria

1.31

 Criteria

1.26

criteria

1.21

Criteria

1.19

 criterion

1.16

 jawa

1.15

 CRITERIA

1.09

 Criterion

1.07

 jaya

1.02

riteria

1.00

Activations Density 0.106%

specific criteria listed in documents

No Comments

No Known Activations