INDEX

Explanations

language indicating implied meanings and implications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.56

-1.07

/***

-0.97

<?

-0.94

/*!

-0.93

ⓧ

-0.78

<?

-0.64

/**

-0.63

 rehabilitate

-0.60

ostringstream

-0.60

POSITIVE LOGITS

 palio

1.05

 signora

0.98

 riva

0.97

 pesante

0.96

 Czechos

0.96

 dott

0.94

 paradiso

0.94

 borsa

0.94

 incess

0.94

 indeb

0.94

Activations Density 0.043%

language indicating implied meanings and implications

No Comments

No Known Activations