INDEX

Explanations

terms related to immediate actions or availability

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>

-3.21

/***

-0.86

-0.83

<?

-0.79

/**

-0.78

ⓧ

-0.73

<?

-0.71

Тру

-0.64

Skocz

-0.61

 deepen

-0.61

POSITIVE LOGITS

 wien

1.44

 stockholm

1.39

 frankfurt

1.38

 bayern

1.30

 kram

1.30

Hæ

1.25

 lele

1.24

 meis

1.23

 kaos

1.21

 Græ

1.21

Activations Density 0.117%

terms related to immediate actions or availability

No Comments

No Known Activations